A Deep Residual PLS for Data-Driven Quality Prediction Modeling in Industrial Process

Partial least squares(PLS)model is the most typical data-driven method for quality-related industrial tasks like soft sensor.However,only linear relations are captured between the input and output data in the PLS.It is difficult to obtain the remaining nonlinear information in the residual subspaces,which may deteriorate the prediction performance in complex industrial processes.To fully utilize data information in PLS residual subspaces,a deep residual PLS(DRPLS)framework is proposed for quality prediction in this paper.Inspired by deep learning,DRPLS is designed by stacking a number of PLSs successively,in which the input residuals of the previous PLS are used as the layer connection.To enhance representation,nonlinear function is applied to the input residuals before using them for stacking highlevel PLS.For each PLS,the output parts are just the output residuals from its previous PLS.Finally,the output prediction is obtained by adding the results of each PLS.The effectiveness of the proposed DRPLS is validated on an industrial hydrocracking process.

A computational model of the human glucose-insulin regulatory system

Objective：A computational model of insulin secretion and glucose metabolism for assisting the diagnosis of diabetes mellitus in clinical research is introduced.The proposed method for the estimation of parameters for a system of ordinary differential equations（ODEs）that represent the time course of plasma glucose and insulin concentrations during glucose tolerance test（GTT）in physiological studies is presented.The aim of this study was to explore how to interpret those laboratory glucose and insulin data as well as enhance the Ackerman mathematical model.Methods：Parameters estimation for a system of ODEs was performed by minimizing the sum of squared residuals（SSR）function,which quantifies the difference between theoretical model predictions and GTT＇s experimental observations.Our proposed perturbation search and multiple-shooting methods were applied during the estimating process.Results：Based on the Ackerman＇s published data,we estimated the key parameters by applying R-based iterative computer programs.As a result,the theoretically simulated curves perfectly matched the experimental data points.Our model showed that the estimated parameters,computed frequency and period values,were proven a good indicator of diabetes.Conclusion：The present paper introduces a computational algorithm to biomedical problems,particularly to endocrinology and metabolism fields,which involves two coupled differential equations with four parameters describing the glucose-insulin regulatory system that Ackerman proposed earlier.The enhanced approach may provide clinicians in endocrinology and metabolism field insight into the transition nature of human metabolic mechanism from normal to impaired glucose tolerance.

A corrected method of distorted printed circuit board image

This paper proposes a corrected method of distorted image based on adaptive control. First, the adaptive control relationship of pixel point positions between distorted image and its corrected image is given by using polynomial fitting, thus control point pairs between the distorted image and its corrected image are found. Secondly, the value of both image distortion centre and polynomial coefficient is obtained with least square method, thus the relationship of each control point pairs is deduced. In the course of distortion image processing, the gray value of the corrected image is changed into integer with bilinear interpolation. Finally, the experiments are performed to correct two distorted printed circuit board images. The results are perfect and the mean square errors of residual error are tiny.

Correlation-weighted least squares residual algorithm for RAIM

The Least Squares Residual(LSR)algorithm,one of the classical Receiver Autonomous Integrity Monitoring(RAIM)algorithms for Global Navigation Satellite System(GNSS),presents a high Missed Detection Risk(MDR)for a large-slope faulty satellite and a high False Alarm Risk(FAR)for a small-slope faulty satellite.From the theoretical analysis of the high MDR and FAR cause,the optimal slope is determined,and thereby the optimal test statistic for fault detection is conceived,which can minimize the FAR with the MDR not exceeding its allowable value.To construct a test statistic approximate to the optimal one,the CorrelationWeighted LSR(CW-LSR)algorithm is proposed.The CW-LSR test statistic remains the sum of pseudorange residual squares,but the square for the most potentially faulty satellite,judged by correlation analysis between the pseudorange residual and observation error,is weighted with an optimal-slope-based factor.It does not obey the same distribution but has the same noncentral parameter with the optimal test statistic.The superior performance of the CW-LSR algorithm is verified via simulation,both reducing the FAR for a small-slope faulty satellite with the MDR not exceeding its allowable value and reducing the MDR for a large-slope faulty satellite at the expense of FAR addition.

An enhanced least squares residual RAIM algorithm based on optimal decentralized factor

The Least Squares Residual(LSR)algorithm is commonly used in the Receiver Autonomous Integrity Monitoring(RAIM).However,LSR algorithm presents high Missed Detection Risk(MDR)caused by a large-slope faulty satellite and high False Alert Risk(FAR)caused by a small-slope faulty satellite.In this paper,the LSR algorithm is improved to reduce the MDR for a large-slope faulty satellite and the FAR for a small-slope faulty satellite.Based on the analysis of the vertical critical slope,the optimal decentralized factor is defined and the optimal test statistic is conceived,which can minimize the FAR with the premise that the MDR does not exceed its allowable value of all three directions.To construct a new test statistic approximating to the optimal test statistic,the Optimal Decentralized Factor weighted LSR(ODF-LSR)algorithm is proposed.The new test statistic maintains the sum of pseudo-range residual squares,but the specific pseudo-range residual is weighted with a parameter related to the optimal decentralized factor.The new test statistic has the same decentralized parameter with the optimal test statistic when single faulty satellite exists,and the difference between the expectation of the new test statistic and the optimal test statistic is the minimum when no faulty satellite exists.The performance of the ODFLSR algorithm is demonstrated by simulation experiments.

Investigation of Surface Integrity on TC17 Titanium Alloy Treated by Square-spot Laser Shock Peening

Laser shock peening（LSP） is an innovative surface treatment method,which has been shown to greatly improve the fatigue life of many metallic components.This work investigates surface integrity of TC17 titanium alloy treated by LSP with innovative square laser spot.Nd：glass laser with duration of 30 ns and spot size of 4 mm×4 mm is applied.The surface morphology and surface residual stress of the TC17 titanium alloy,treated with varying peening parameters such as laser power density and overlapping ratio,have been studied in detail.The results show that laser pulse energy greatly influences surface morphology and surface residual stress around single-spot treated areas,and compressive residual stresses are saturated as laser pulse energy is over 55 J.There are significantly different surface morphologies and residual stress distributions at the overlapped areas with different overlapping ratios.A relative smooth surface is produced with uniform compressive residual stress distribution at an overlapping ratio of 8 %.The experiment of residual stress relaxation is implemented by measuring residual stress at the center of four overlapped spots and by four point bending fatigue test at the frequency of 105 Hz.The compressive residual stresses induced by LSP are found to relax quite slowly under cyclic fatigue loading.