scholarly journals Multiway dynamic nonlinear global neighborhood preserving embedding method for monitoring batch process

2020 ◽  
Vol 53 (5-6) ◽  
pp. 994-1006
Author(s):  
Yongyong Hui ◽  
Xiaoqiang Zhao
Keyword(s):  
Infinite Order ◽  
Dimensional Space ◽  
Batch Process ◽  
Mapping Method ◽  
Process Variables ◽  
Nonlinear Method ◽  
Nonlinear Characteristics ◽  
Embedding Method ◽  
Physical Constraints ◽  
Kernel Mapping

Aiming at the dynamic and nonlinear characteristics of batch process, a multiway dynamic nonlinear global neighborhood preserving embedding algorithm is proposed. For the nonlinear batch process monitoring, kernel mapping is widely used to eliminate nonlinearity by projecting the data into high-dimensional space, but the nonlinear relationships between batch process variables are limited by many physical constraints, and the infinite-order mapping is inefficient and redundant. Compared with the basic kernel mapping method which provides an infinite-order nonlinear mapping, the proposed method considers the dynamic and nonlinear characteristics with many physical constraints and preserves the global and local structures concurrently. First, the time-lagged window is used to remove the auto-correlation in time series of process variables. Second, a nonlinear method named constructive polynomial mapping is used to avoid unnecessary redundancy and reduce computational complexity. Third, the global neighborhood preserving embedding method is used to extract structures fully after the dynamic and nonlinear characteristics are processed. Finally, the effects of the proposed algorithm are demonstrated by a mathematical model and the penicillin fermentation process.

scholarly journals Adaptive Intelligent Welding Manufacturing

2021 ◽  
Vol 100 (01) ◽  
pp. 63-83
Author(s):  
YUMING ZHANG ◽  
◽  
QIYUE WANG ◽  
YUKANG LIU
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Deep Learning ◽  
Welding Process ◽  
Welding Parameters ◽  
Weld Quality ◽  
Robotic Welding ◽  
Process Variables ◽  
Physical Constraints ◽  
Needed Information

Optimal design of the welding procedure gives the desired welding results under nominal welding conditions. During manufacturing, where the actual welding manufacturing conditions often deviate from the nominal ones used in the design, applying the designed procedure will produce welding results that are different from the desired ones. Adaption is needed to make corrections and adjust some of the welding parameters from those specified in the design. This is adaptive welding. While human welders can be adaptive to make corrections and adjustments, their performance is limited by their physical constraints and skill level. To be adaptive, automated and robotic welding systems require abilities in sensing the welding process, extracting the needed information from signals from the sensors, predicting the responses of the welding process to the adjustments on welding parameters, and optimizing the adjustments. This results in the application of classical sensing, modeling of process dynamics, and control system design. In many cases, the needed information for the weld quality and process variables of our concern is not easy to extract from the sensor’s data. Studies are needed to propose the phenomena to sense and establish the scientific foundation to correlate them to the weld quality or process variables of our concern. Such studies can be labor intensive, and a more automated approach is needed. Analysis suggests that artificial intelligence and machine learning, especially deep learning, can help automate the learning such that the needed intelligence for robotic welding adaptation can be directly and automatically learned from experimental data after the physical phenomena being represented by the experimental data has been appropriately selected to make sure they are fundamentally correlated to that with which we are concerned. Some adaptation abilities may also be learned from skilled human welders. In addition, human-robot collaborative welding may incorporate adaptations from humans with the welding robots. This paper analyzes and identifies the challenges in adaptive robotic welding, reviews efforts devoted to solve these challenges, analyzes the principles and nature of the methods behind these efforts, and introduces modern approaches, including machine learning/deep learning, learning from humans, and human-robot collaboration, to solve these challenges.

scholarly journals Fault Identification Based on Local Feature Correlation

2022 ◽  
pp. 119-146
Author(s):  
Jing Wang ◽  
Jinglin Zhou ◽  
Xiaolu Chen
Keyword(s):  
Data Processing ◽  
High Dimension ◽  
Dimensional Space ◽  
Original Data ◽  
Mapping Method ◽  
Kernel Functions ◽  
High Dimensional ◽  
Monitoring Methods ◽  
Multivariate Statistical ◽  
Low Dimensional

AbstractIndustrial data variables show obvious high dimension and strong nonlinear correlation. Traditional multivariate statistical monitoring methods, such as PCA, PLS, CCA, and FDA, are only suitable for solving the high-dimensional data processing with linear correlation. The kernel mapping method is the most common technique to deal with the nonlinearity, which projects the original data in the low-dimensional space to the high-dimensional space through appropriate kernel functions so as to achieve the goal of linear separability in the new space. However, the space projection from the low dimension to the high dimension is contradictory to the actual requirement of dimensionality reduction of the data. So kernel-based method inevitably increases the complexity of data processing.

Formulation of a New Trend Cumulative Sum Chart to Monitor Batch Process Variables

2018 ◽  
Vol 57 (18) ◽  
pp. 6303-6316 ◽  
Author(s):  
Laibin Zhang ◽  
Xi Ma ◽  
Jinqiu Hu ◽  
Shaohua Dong ◽  
Ahmet Palazoglu
Keyword(s):  
Batch Process ◽  
Process Variables ◽  
Cumulative Sum

scholarly journals Emotion Recognition Based on Multichannel Physiological Signals with Comprehensive Nonlinear Processing

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3886 ◽  
Author(s):  
Xingxing Zhang ◽  
Chao Xu ◽  
Wanli Xue ◽  
Jing Hu ◽  
Yongchuan He ◽  
...  
Keyword(s):  
Emotion Recognition ◽  
Dimensional Space ◽  
Principal Component ◽  
Ensemble Classifier ◽  
Feature Reduction ◽  
Kernel Principal Component Analysis ◽  
Gradient Boosting ◽  
Nonlinear Method ◽  
Nonlinear Processing ◽  
The One

Multichannel physiological datasets are usually nonlinear and separable in the field of emotion recognition. Many researchers have applied linear or partial nonlinear processing in feature reduction and classification, but these applications did not work well. Therefore, this paper proposed a comprehensive nonlinear method to solve this problem. On the one hand, as traditional feature reduction may cause the loss of significant amounts of feature information, Kernel Principal Component Analysis (KPCA) based on radial basis function (RBF) was introduced to map the data into a high-dimensional space, extract the nonlinear information of the features, and then reduce the dimension. This method can provide many features carrying information about the structure in the physiological dataset. On the other hand, considering its advantages of predictive power and feature selection from a large number of features, Gradient Boosting Decision Tree (GBDT) was used as a nonlinear ensemble classifier to improve the recognition accuracy. The comprehensive nonlinear processing method had a great performance on our physiological dataset. Classification accuracy of four emotions in 29 participants achieved 93.42%.

GENERALIZED WEIERSTRASS–MANDELBROT FUNCTION MODEL FOR ACTUAL STOCKS MARKETS INDEXES WITH NONLINEAR CHARACTERISTICS

Fractals ◽  
2015 ◽  
Vol 23 (02) ◽  
pp. 1550006 ◽  
Author(s):  
L. ZHANG ◽  
C. YU ◽  
J. Q. SUN
Keyword(s):  
Fractal Dimension ◽  
Stock Market ◽  
Financial Markets ◽  
Hurst Exponent ◽  
Dimensional Space ◽  
Dynamical Behavior ◽  
Three Dimensional ◽  
Nonlinear Characteristics ◽  
Market Indexes ◽  
Three Dimensional Space

It is difficult to simulate the dynamical behavior of actual financial markets indexes effectively, especially when they have nonlinear characteristics. So it is significant to propose a mathematical model with these characteristics. In this paper, we investigate a generalized Weierstrass–Mandelbrot function (WMF) model with two nonlinear characteristics: fractal dimension D where 2 > D > 1.5 and Hurst exponent (H) where 1 > H > 0.5 firstly. And then we study the dynamical behavior of H for WMF as D and the spectrum of the time series γ change in three-dimensional space, respectively. Because WMF and the actual stock market indexes have two common features: fractal behavior using fractal dimension and long memory effect by Hurst exponent, we study the relationship between WMF and the actual stock market indexes. We choose a random value of γ and fixed value of D for WMF to simulate the S&P 500 indexes at different time ranges. As shown in the simulation results of three-dimensional space, we find that γ is important in WMF model and different γ may have the same effect for the nonlinearity of WMF. Then we calculate the skewness and kurtosis of actual Daily S&P 500 index in different time ranges which can be used to choose the value of γ. Based on these results, we choose appropriate γ, D and initial value into WMF to simulate Daily S&P 500 indexes. Using the fit line method in two-dimensional space for the simulated values, we find that the generalized WMF model is effective for simulating different actual stock market indexes in different time ranges. It may be useful for understanding the dynamical behavior of many different financial markets.

Robust Facial Image Super-Resolution by Kernel Locality-Constrained Coupled-Layer Regression

2021 ◽  
Vol 21 (3) ◽  
pp. 1-15
Author(s):  
Guangwei Gao ◽  
Dong Zhu ◽  
Huimin Lu ◽  
Yi Yu ◽  
Heyou Chang ◽  
...  
Keyword(s):  
Dimensional Space ◽  
Contextual Information ◽  
Super Resolution ◽  
Target Position ◽  
Representation Learning ◽  
Facial Image ◽  
Nonlinear Characteristics ◽  
Resolution Scheme ◽  
Image Super Resolution ◽  
Low Dimensional

Super-resolution methods for facial image via representation learning scheme have become very effective methods due to their efficiency. The key problem for the super-resolution of facial image is to reveal the latent relationship between the low-resolution ( LR ) and the corresponding high-resolution ( HR ) training patch pairs. To simultaneously utilize the contextual information of the target position and the manifold structure of the primitive HR space, in this work, we design a robust context-patch facial image super-resolution scheme via a kernel locality-constrained coupled-layer regression (KLC2LR) scheme to obtain the desired HR version from the acquired LR image. Here, KLC2LR proposes to acquire contextual surrounding patches to represent the target patch and adds an HR layer constraint to compensate the detail information. Additionally, KLC2LR desires to acquire more high-frequency information by searching for nearest neighbors in the HR sample space. We also utilize kernel function to map features in original low-dimensional space into a high-dimensional one to obtain potential nonlinear characteristics. Our compared experiments in the noisy and noiseless cases have verified that our suggested methodology performs better than many existing predominant facial image super-resolution methods.

A Low Dimensional Embedding Method for Combining Clusterings

2011 ◽  
Vol 201-203 ◽  
pp. 2517-2520
Author(s):  
Sen Xu ◽  
Tian Zhou ◽  
Hua Long Yu
Keyword(s):  
Machine Learning ◽  
Spectral Clustering ◽  
Dimensional Space ◽  
Clustering Algorithms ◽  
Critical Problem ◽  
Embedding Method ◽  
Superior Result ◽  
Multiple Clusterings ◽  
Low Dimensional

Clustering combination has recently become a hotspot in machine learning, while its critical problem lies on how to combine multiple clusterings to yield a final superior result. In this paper, a low dimensional embedding method is proposed. It first obtains the low dimensional embeddings of hyperedges by performing spectral clustering algorithms and then obtains the low dimensional embeddings of objects indirectly by composition of mappings and finally performs K-means algorithm to cluster the objects according to their coordinates in the low dimensional space. Experimentally the proposed method is shown to perform well.

scholarly journals Nonspontaneous and multilayer adsorption of malachite green dye by Acacia nilotica waste with dominance of physisorption

2017 ◽  
Vol 76 (7) ◽  
pp. 1805-1815 ◽  
Author(s):  
M. T. Amin ◽  
A. A. Alazba ◽  
M. Shafiq
Keyword(s):  
Malachite Green ◽  
Batch Process ◽  
Acacia Nilotica ◽  
Process Variables ◽  
Free Energy Of Adsorption ◽  
Multilayer Adsorption ◽  
Adsorption Reaction ◽  
Malachite Green Dye ◽  
Opposite Trend ◽  
Adsorption Data

Adsorption of the hazardous dye malachite green (MG) by Acacia nilotica (AN) waste was investigated. Batch process variables for the adsorption of MG by AN were optimized. The mechanisms involved in the adsorption of MG by AN were explored using isotherms and kinetic models. The thermodynamic parameters were calculated to determine the spontaneity and thermal nature of the MG adsorption reaction. The maximum equilibrium adsorption capacity of AN was found to be 113.26 mg/g at 30 °C. The MG adsorption data revealed that AN adsorbs MG by multilayer adsorption, as shown by the better fit of the data to the Freundlich and Halsey models (R2 = 0.99) rather than to the Langmuir model. Multilayer adsorption involves physisorption, which was confirmed by the E value (mean free energy of adsorption) of the Dubinin–Radushkevich model (6.52 kJ/mol). Surface diffusion was found to be the main driving force for MG adsorption by AN. The MG adsorption reaction was endothermic, based on the enthalpy, and was controlled by the entropy of the system in the T1 temperature range (30 to 40 °C), while the opposite trend was observed in the T2 range (40 to 50 °C). Moreover, MG adsorption by AN was found to be nonspontaneous at all temperatures.

Sign in / Sign up

Export Citation Format

Share Document