Ironmaking process(IP)is indispensable to modern iron and steel industry,where real-time monitoring is crucial for achieving high molten iron quality(MIQ)with low energy consumption.While neural network-based models s...Ironmaking process(IP)is indispensable to modern iron and steel industry,where real-time monitoring is crucial for achieving high molten iron quality(MIQ)with low energy consumption.While neural network-based models show some promising results,they are generally limited by non-negligible drawbacks such as interpretability issues of feature learning.To address these issues,we propose a novel concept based on the shallow-to-deep correlation network representation regression(Sh-to-De CNRR).Our approach,shallow correlation network representation regression(ShCNRR),combines neural network and canonical correlation analysis thoughts to generate explainable features via shallow correlation network representation(CNR).A twin inverse network is then derived to obtain the explicit model output,leveraging the shallow CNR.To capture deeper nonlinear information,we extend ShCNRR into a hierarchical deep correlation network representation regression(DeCNRR)model that features stacked neural networks,enabling us to learn deeper CNR from process data.The feasibility and advantages of our proposals are validated by theoretical derivations and practical IP cases,which contain one MIQ regression and three MIQ-related fault detection tasks.The results reveal that highly fused statistical and neural network models yield superior monitoring performance compared to current state-of-the-art models,while statistical tests verify the convincing feature mining.展开更多
The composite material layering process has attracted considerable attention due to its production advantages,including high scalability and compatibility with a wide range of raw materials.However,changes in process ...The composite material layering process has attracted considerable attention due to its production advantages,including high scalability and compatibility with a wide range of raw materials.However,changes in process conditions can lead to degradation in layer quality and non-uniformity,highlighting the need for real-time monitoring to improve overall quality and efficiency.In this study,an AI-based monitoring system was developed to evaluate layer width and assess quality in real time.Three deep learning models Faster Region-based Convolutional Neural Network(R-CNN),You Only Look Once version 8(YOLOv8),and Single Shot MultiBox Detector(SSD)were compared,and YOLOv8 was ultimately selected for its superior speed,flexibility,and scalability.The selected model was integrated into a user-friendly interface.To verify the reliability of the system,bead width control experiments were conducted,which identified feed speed and extrusion speed as the key process parameters.Accordingly,a Central Composite Design(CCD)experimental plan with 13 conditions was applied to evaluate layer width and validate the system’s reliability.Finally,the proposed system was applied to the additive manufacturing of an aerospace component,where it successfully detected bead width deviations during printing and enabled stable fabrication with a maximum geometric deviation of approximately 6 mm.These findings demonstrate the critical role of real-time monitoring of layer width and quality in improving process stability and final product quality in composite material additive manufacturing.展开更多
A new modeling and monitoring approach for multi-mode processes is proposed.The method of similarity measure(SM) and kernel principal component analysis(KPCA) are integrated to construct SM-KPCA monitoring scheme,wher...A new modeling and monitoring approach for multi-mode processes is proposed.The method of similarity measure(SM) and kernel principal component analysis(KPCA) are integrated to construct SM-KPCA monitoring scheme,where SM method serves as the separation of common subspace and specific subspace.Compared with the traditional methods,the main contributions of this work are:1) SM consisted of two measures of distance and angle to accommodate process characters.The different monitoring effect involves putting on the different weight,which would simplify the monitoring model structure and enhance its reliability and robustness.2) The proposed method can be used to find faults by the common space and judge which mode the fault belongs to by the specific subspace.Results of algorithm analysis and fault detection experiments indicate the validity and practicability of the presented method.展开更多
The kernel principal component analysis （KPCA） method employs the first several kernel principal components （KPCs）, which indicate the most variance information of normal observations for process monitoring, but m...The kernel principal component analysis （KPCA） method employs the first several kernel principal components （KPCs）, which indicate the most variance information of normal observations for process monitoring, but may not reflect the fault information. In this study, sensitive kernel principal component analysis （SKPCA） is proposed to improve process monitoring performance, i.e., to deal with the discordance of T2 statistic and squared prediction error SVE statistic and reduce missed detection rates. T2 statistic can be used to measure the variation di rectly along each KPC and analyze the detection performance as well as capture the most useful information in a process. With the calculation of the change rate of T2 statistic along each KPC, SKPCA selects the sensitive kernel principal components for process monitoring. A simulated simple system and Tennessee Eastman process are employed to demonstrate the efficiency of SKPCA on online monitoring. The results indicate that the monitoring performance is improved significantly.展开更多
Due to higher demands on product diversity,flexible shift between productions of different products in one equipment becomes a popular solution,resulting in existence of multiple operation modes in a single process.In...Due to higher demands on product diversity,flexible shift between productions of different products in one equipment becomes a popular solution,resulting in existence of multiple operation modes in a single process.In order to handle such multi-mode process,a novel double-layer structure is proposed and the original data are decomposed into common and specific characteristics according to the relationship between variables among each mode.In addition,both low and high order information are considered in each layer.The common and specific information within each mode can be captured and separated into several subspaces according to the different order information.The performance of the proposed method is further validated through a numerical example and the Tennessee Eastman(TE)benchmark.Compared with previous methods,superiority of the proposed method is validated by the better monitoring results.展开更多
Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems,such as thermal power plants being studied in this work.Industrial processes are inherently d...Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems,such as thermal power plants being studied in this work.Industrial processes are inherently dynamic and need to be monitored using dynamic algorithms.Mainstream dynamic algorithms rely on concatenating current measurement with past data.This work proposes a new,alternative dynamic process monitoring algorithm,using dot product feature analysis(DPFA).DPFA computes the dot product of consecutive samples,thus naturally capturing the process dynamics through temporal correlation.At the same time,DPFA's online computational complexity is lower than not just existing dynamic algorithms,but also classical static algorithms(e.g.,principal component analysis and slow feature analysis).The detectability of the new algorithm is analyzed for three types of faults typically seen in process systems:sensor bias,process fault and gain change fault.Through experiments with a numerical example and real data from a thermal power plant,the DPFA algorithm is shown to be superior to the state-of-the-art methods,in terms of better monitoring performance(fault detection rate and false alarm rate)and lower computational complexity.展开更多
This study aims to enhance the digital drilling process monitoring(DPM)or monitoring while drilling(MWD)technique,which is a widely recognized method in geological exploration for evaluating rock mass quality.First,ro...This study aims to enhance the digital drilling process monitoring(DPM)or monitoring while drilling(MWD)technique,which is a widely recognized method in geological exploration for evaluating rock mass quality.First,robust displacement and torque measurement facilities for rotary-core drilling are discussed.The conventional cable encoder for displacement measurement is replaced with a magnetostrictive displacement sensor,which is more reliable in harsh field drilling environments.This enables the measurement of the bit position with an accuracy of<1 mm.Most importantly,this new instrument is proven to be successful in improving the detection of structural discontinuities with thicknesses>1 mm.In addition,by measuring the electric current of the driving motor,the torque applied to the bit is conveniently and accurately converted.These innovations ensure high-quality data collection for DPM practices.Second,two indices derived from DPM are proposed to quantitatively describe rock mass quality.The specific energy index(SEI)and specific penetration index(SPI)are based on the principles of energy conservation and Mohr-Coulomb failure criterion,respectively.Extensive field tests conducted in a dam grouting area confirm a linear relationship between the thrust force and penetration per rotation,and between the torque and penetration per rotation.The correlation ratios of the related regressions are typically>0.9.These two indices allow for the quantitative interpretation of DPM data into rock mechanics characteristics,such as uniaxial compressive strength,rock quality designation(RQD),and rock mass permeability,eliminating the need for subjective judgment normally involved in the currently used rock mass quality rating approaches.展开更多
Difficulties in the geometric and performance control of wire laser additive manufacturing have hindered its widespread application.In this study,an in situ process monitoring system that combines a machine vision-bas...Difficulties in the geometric and performance control of wire laser additive manufacturing have hindered its widespread application.In this study,an in situ process monitoring system that combines a machine vision-based interlayer height controller(IHC)and P-controller-based melt pool temperature controller(MTC)was developed to improve the vertical dimensional accuracy and mechanical properties of off-axis fine-wire laser-directed energy deposition(OAFW-LDED)for 316 L thin-walled parts.The IHC effectively mitigates external defect inheritance,while its synergy with the MTC ensures process stability,improving the vertical dimensional accuracy to±0.2 mm.Grain refinement was achieved by controlling the thermal input to optimize the thermal history and heat accumulation.A heterogeneous microstructure with alternating coarse and fine grains was observed and intergranular thermal cracking was suppressed.The yield and tensile strengths increased from 262 to 416 MPa to 313 and 516 MPa,respectively,with improved consistency in the yield strength between the top and bottom sections.However,excessive laser heat input caused interlayer cracks.Conversely,increasing the heat input through substrate preheating did not induce additional cracks and improved the overall hardness consistency of the thin-walled samples.Therefore,this study proposes a new formability control strategy for OAFW-LDEDs of thin-walled parts.展开更多
The increasing demand for unconventional oil and gas resources,especially oil shale,has highlighted the urgent need to develop rapid and accurate strata characterization methods.This paper is the first case and examin...The increasing demand for unconventional oil and gas resources,especially oil shale,has highlighted the urgent need to develop rapid and accurate strata characterization methods.This paper is the first case and examines the drilling process monitoring(DPM)method as a digital,accurate,cost-effective method to characterize oil shale reservoirs in the Ordos Basin,China.The digital DPM method provides real-time in situ testing of the relative variation in rock mechanical strength along the drill bit depth.Furthermore,it can give a refined rock quality designation based on the DPM zoning result(RQD(V_(DPM)))and a strength-grade characterization at the site.Oil shale has high heterogeneity and low strata strength.The digital results are further compared and verified with manual logging,cored samples,and digital panoramic borehole cameras.The findings highlight the innovative potential of the DPM method in identifying the zones of oil shale reservoir along the drill bit depth.The digital results provide a better understanding of the oil shale in Tongchuan and the potential for future oil shale exploration in other regions.展开更多
The evaluation of rock mass quality and its mechanical properties is crucial for tunnel construction.The basic quality(BQ)method is the national standard for rock mass classification in China,with the BQ value determi...The evaluation of rock mass quality and its mechanical properties is crucial for tunnel construction.The basic quality(BQ)method is the national standard for rock mass classification in China,with the BQ value determined by the uniaxial compressive strength(UCS)and the integrity index(Kv).However,traditional rock mechanics testing methods have inherent limitations,which complicate the rapid evaluation of rock mass quality at tunnel sites.Digital drilling process monitoring(DPM)offers a novel approach for evaluating rock mass quality and its mechanical properties.A hydraulic rotary drilling rig,equipped with the DPM system,was used to conduct digital drilling tests at the tunnel face.The DPM data for the net drilling process and each sub-process were then analyzed.The correlations between DPM parameter indices and rock mechanical parameters were investigated.Finally,the rock mass quality and its mechanical properties along three boreholes were evaluated.The results indicate that drilling speed in the linear zone(V_(DPM))is quantitatively correlated with rock UCS.Higher UCS values of the drilled rocks correspond to lower V_(DPM) values of the drilling rig.The variability in specific energy is associated with structural disturbances within the rock mass.There is an approximately linear relationship between the standard deviation of normalized specific energy and rock mass K_(v) across the three boreholes.The rock mass quality along drilling depth generally ranges from good(Ⅰ-Ⅱ)to poor(Ⅲ-Ⅴ).This digitalization method provides more detailed information for tunnel stability analysis and design optimization than geological survey data.展开更多
Environmental protection requires identifying,investigating,and raising awareness about safeguarding nature from the harmful effects of both anthropogenic and natural events.This process of environmental protection is...Environmental protection requires identifying,investigating,and raising awareness about safeguarding nature from the harmful effects of both anthropogenic and natural events.This process of environmental protection is essential for maintaining human well-being.In this context,it is critical to monitor and safeguard the personal environment,which includes maintaining a healthy diet and ensuring plant safety.Living in a balanced environment and ensuring the safety of plants for green spaces and a healthy diet require controlling the nature and quality of the soil in our environment.To ensure soil quality,it is imperative to monitor and assess the levels of various soil parameters.Therefore,an Optimized Reduced Kernel Partial Least Squares(ORKPLS)method is proposed to monitor and control soil parameters.This approach is designed to detect increases or deviations in soil parameter quantities.A Tabu search approach was used to select the appropriate kernel parameter.Subsequently,soil analyses were conducted to evaluate the performance of the developed techniques.The simulation results were analyzed and compared.Through this study,deficiencies or exceedances in soil parameter quantities can be identified.The proposed method involves determining whether each soil parameter falls within a normal range.This allows for the assessment of soil parameter conditions based on the principle of fault detection.展开更多
A novel online process monitoring and fault diagnosis method of condenser based on kernel principle component analysis （KPCA） and Fisher discriminant analysis （FDA） is presented. The basic idea of this method is：...A novel online process monitoring and fault diagnosis method of condenser based on kernel principle component analysis （KPCA） and Fisher discriminant analysis （FDA） is presented. The basic idea of this method is： First map data from the original space into high-dimensional feature space via nonlinear kernel function and then extract optimal feature vector and discriminant vector in feature space and calculate the Euclidean distance between feature vectors to perform process monitoring. Similar degree between the present discriminant vector and optimal discriminant vector of fault in historical dataset is used for diagnosis. The proposed method can effectively capture the nonlinear relationship among process variables. Simulating results of the turbo generator＇s fault data set prove that the proposed method is effective.展开更多
Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exp...Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exponentially weighted moving average(SGLGEWMA)control chart,incorporating a Sparse Group Lasso penalty,which is capable of detecting shifts in the covariance matrix across a wide range of data types,including discrete,continuous,and mixed distributions.The proposed approach projects multivariate data into a Euclidean space and then computes an approximate Alt’s likelihood ratio,regularized via the Sparse Group Lasso.The resulting EWMA statistic monitors process shifts.Monte Carlo simulations demonstrate that SGLGEWMA outperforms both the Lasso-based LGShewhart and the Ridge-based RGEWMA control charts under various distributions,with enhanced efficacy in high-dimensional scenarios.Sensitivity analyses are performed on the tuning parameters(λ_(1),λ_(2))and smoothing parameterρ,to evaluate their impact on monitoring performance.Additionally,a simulation study and an illustrative example involving covariance monitoring in wafer semiconductor manufacturing are presented to demonstrate the practical application of the proposed chart.Empirical results confirm that the proposed control chart promptly identifies abnormal fluctuations and issues timely alerts,highlighting both its theoretical significance and practical utility.展开更多
Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the t...Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the two methods is that the components of PCA are still dependent while ICA has no orthogonality constraint and its latentvariables are independent. Process monitoring with PCA often supposes that process data or principal components is Gaussian distribution. However, this kind of constraint cannot be satisfied by several practical processes. To ex-tend the use of PCA, a nonparametric method is added to PCA to overcome the difficulty, and kernel density estimation （KDE） is rather a good choice. Though ICA is based on non-Gaussian distribution intormation, .KDE can help in the close monitoring of the data. Methods, such as PCA, ICA, PCA.with .KDE（KPCA）, and ICA with KDE,（KICA）, are demonstrated and. compared by applying them to a practical industnal Spheripol craft polypropylene catalyzer reactor instead of a laboratory emulator.展开更多
In the past decades, on-line monitoring of batch processes using multi-way independent component analysis （MICA） has received considerable attention in both academia and industry. This paper focuses on two troubleso...In the past decades, on-line monitoring of batch processes using multi-way independent component analysis （MICA） has received considerable attention in both academia and industry. This paper focuses on two troublesome issues concerning selecting dominant independent components without a standard criterion and deter- mining the control limits of monitoring statistics in the presence of non-Gaussian distribution. To optimize the number of key independent components~ we introctuce-anoveiconcept of-system-cleviation, which is ab^e＇io＇evalu[ ate the reconstructed observations with different independent components. The monitored statistics arc transformed to Gaussian distribution data by means of Box-Cox transformation, which helps readily determine the control limits. The proposed method is applied to on-line monitoring of a fed-hatch penicillin fermentation simulator, and the ex- _perimental results indicate the advantages of the improved MICA monitoring compared to the conventional methods.展开更多
Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares ...Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares (PLS) are surveyed in this paper. The four-step procedure of performing MSPM&C for chemical process, modeling of processes, detecting abnormal events or faults, identifying the variable(s) responsible for the faults and diagnosing the source cause for the abnormal behavior, is analyzed. Several main research directions of MSPM&C reported in the literature are discussed, such as multi-way principal component analysis (MPCA) for batch process, statistical monitoring and control for nonlinear process, dynamic PCA and dynamic PLS, and on-line quality control by inferential models. Industrial applications of MSPM&C to several typical chemical processes, such as chemical reactor, distillation column, polymerization process, petroleum refinery units, are summarized. Finally, some concluding remarks and future considerations are made.展开更多
Process monitoring techniques are of paramount importance in the chemical industry to improve both the product quality and plant safety.Small or incipient irregularities may lead to severe degradation in complex chemi...Process monitoring techniques are of paramount importance in the chemical industry to improve both the product quality and plant safety.Small or incipient irregularities may lead to severe degradation in complex chemical processes,and the conventional process monitoring techniques cannot detect these irregularities.In this study to improve the performance of monitoring,an online multiscale fault detection approach is proposed by integrating multiscale principal component analysis(MSPCA) with cumulative sum(CUSUM) and exponentially weighted moving average(EWMA) control charts.The new Hotelling's T~2 and square prediction error(SPE) based fault detection indices are proposed to detect the incipient irregularities in the process data.The performance of the proposed fault detection methods was tested for simulated data obtained from the CSTR system and compared to that of conventional PCA and MSPCA based methods.The results demonstrate that the proposed EWMA based MSPCA fault detection method was successful in detecting the faults.Moreover,a comparative study shows that the SPEEWMA monitoring index exhibits a better performance with lower values of missed detections ranging from 0% to 0.80% and false alarms ranging from 0% to 21.20%.展开更多
Multi-way principal component analysis (MPCA) had been successfully applied to monitoring the batch and semi-batch process in most chemical industry. An improved MPCA approach, step-by-step adaptive MPCA (SAMPCA), usi...Multi-way principal component analysis (MPCA) had been successfully applied to monitoring the batch and semi-batch process in most chemical industry. An improved MPCA approach, step-by-step adaptive MPCA (SAMPCA), using the process variable trajectories to monitoring the batch process is presented in this paper. It does not need to estimate or fill in the unknown part of the process variable trajectory deviation from the current time until the end. The approach is based on a MPCA method that processes the data in a sequential and adaptive manner. The adaptive rate is easily controlled through a forgetting factor that controls the weight of past data in a summation. This algorithm is used to evaluate the industrial streptomycin fermentation process data and is compared with the traditional MPCA. The results show that the method is more advantageous than MPCA, especially when monitoring multi-stage batch process where the latent vector structure can change at several points during the batch.展开更多
For complex industrial processes with multiple operational conditions, it is important to develop effective monitoring algorithms to ensure the safety of production processes. This paper proposes a novel monitoring st...For complex industrial processes with multiple operational conditions, it is important to develop effective monitoring algorithms to ensure the safety of production processes. This paper proposes a novel monitoring strategy based on fuzzy C-means. The high dimensional historical data are transferred to a low dimensional subspace spanned by locality preserving projection. Then the scores in the novel subspace are classified into several overlapped clusters, each representing an operational mode. The distance statistics of each cluster are integrated though the membership values into a novel BID (Bayesian inference distance) monitoring index. The efficiency and effectiveness of the proposed method are validated though the Tennessee Eastman benchmark process.展开更多
For the complex batch process with characteristics of unequal batch data length,a novel data-driven batch process monitoring method is proposed based on mixed data features analysis and multi-way kernel entropy compon...For the complex batch process with characteristics of unequal batch data length,a novel data-driven batch process monitoring method is proposed based on mixed data features analysis and multi-way kernel entropy component analysis(MDFA-MKECA)in this paper.Combining the mechanistic knowledge,different mixed data features of each batch including statistical and thermodynamics entropy features,are extracted to finish data pre-processing.After that,MKECA is applied to reduce data dimensionality and finally establish a monitoring model.The proposed method is applied to a reheating furnace industry process,and the experimental results demonstrate that the MDFA-MKECA method can reduce the calculated amount and effectively provide on-line monitoring of the batch process.展开更多
基金supported in part by the Pioneer Research and Development Program of Zhejiang(2025C01021)Zhejiang Province Postdoctoral Research Project Selection Fund(ZJ2025061)+3 种基金the National Science and Technology Major Project-Intelligent Manufacturing Systems and Robotics of China(2025ZD1602000,2025ZD1601800)the National Natural Science Foundation of China(61933015,62273030,62573387)the Natural Science Foundation of Zhejiang province,China(LY24F030004)the Fundamental Research Funds of Zhejiang Sci-Tech University(25222139-Y)。
文摘Ironmaking process(IP)is indispensable to modern iron and steel industry,where real-time monitoring is crucial for achieving high molten iron quality(MIQ)with low energy consumption.While neural network-based models show some promising results,they are generally limited by non-negligible drawbacks such as interpretability issues of feature learning.To address these issues,we propose a novel concept based on the shallow-to-deep correlation network representation regression(Sh-to-De CNRR).Our approach,shallow correlation network representation regression(ShCNRR),combines neural network and canonical correlation analysis thoughts to generate explainable features via shallow correlation network representation(CNR).A twin inverse network is then derived to obtain the explicit model output,leveraging the shallow CNR.To capture deeper nonlinear information,we extend ShCNRR into a hierarchical deep correlation network representation regression(DeCNRR)model that features stacked neural networks,enabling us to learn deeper CNR from process data.The feasibility and advantages of our proposals are validated by theoretical derivations and practical IP cases,which contain one MIQ regression and three MIQ-related fault detection tasks.The results reveal that highly fused statistical and neural network models yield superior monitoring performance compared to current state-of-the-art models,while statistical tests verify the convincing feature mining.
基金support of the Korea Institute of Industrial Technol-ogy as“Development of a remote manufacturing system for high-risk,high-difficulty pipe production processes”(kitech EH-25-0004)supported by the Technology Innovation Program(or Industrial Strategic Technology Development Program)(RS-2023–00237714+2 种基金Development of Dynamic Metrology Tool for CMP Process StabilizationRS-2025–02634755Development of Real-Time Electrical Fire Prevention System Technology Reflecting the Characteristics of Traditional Markets)funded by the Ministry of Trade,Industry&Energy(MOTIE,Republic of Korea).
文摘The composite material layering process has attracted considerable attention due to its production advantages,including high scalability and compatibility with a wide range of raw materials.However,changes in process conditions can lead to degradation in layer quality and non-uniformity,highlighting the need for real-time monitoring to improve overall quality and efficiency.In this study,an AI-based monitoring system was developed to evaluate layer width and assess quality in real time.Three deep learning models Faster Region-based Convolutional Neural Network(R-CNN),You Only Look Once version 8(YOLOv8),and Single Shot MultiBox Detector(SSD)were compared,and YOLOv8 was ultimately selected for its superior speed,flexibility,and scalability.The selected model was integrated into a user-friendly interface.To verify the reliability of the system,bead width control experiments were conducted,which identified feed speed and extrusion speed as the key process parameters.Accordingly,a Central Composite Design(CCD)experimental plan with 13 conditions was applied to evaluate layer width and validate the system’s reliability.Finally,the proposed system was applied to the additive manufacturing of an aerospace component,where it successfully detected bead width deviations during printing and enabled stable fabrication with a maximum geometric deviation of approximately 6 mm.These findings demonstrate the critical role of real-time monitoring of layer width and quality in improving process stability and final product quality in composite material additive manufacturing.
基金Projects(61273163,61325015,61304121)supported by the National Natural Science Foundation of China
文摘A new modeling and monitoring approach for multi-mode processes is proposed.The method of similarity measure(SM) and kernel principal component analysis(KPCA) are integrated to construct SM-KPCA monitoring scheme,where SM method serves as the separation of common subspace and specific subspace.Compared with the traditional methods,the main contributions of this work are:1) SM consisted of two measures of distance and angle to accommodate process characters.The different monitoring effect involves putting on the different weight,which would simplify the monitoring model structure and enhance its reliability and robustness.2) The proposed method can be used to find faults by the common space and judge which mode the fault belongs to by the specific subspace.Results of algorithm analysis and fault detection experiments indicate the validity and practicability of the presented method.
基金Supported by the 973 project of China （2013CB733600）, the National Natural Science Foundation （21176073）, the Doctoral Fund of Ministry of Education （20090074110005）, the New Century Excellent Talents in University （NCET-09-0346）, ＂Shu Guang＂ project （09SG29） and the Fundamental Research Funds for the Central Universities.
文摘The kernel principal component analysis （KPCA） method employs the first several kernel principal components （KPCs）, which indicate the most variance information of normal observations for process monitoring, but may not reflect the fault information. In this study, sensitive kernel principal component analysis （SKPCA） is proposed to improve process monitoring performance, i.e., to deal with the discordance of T2 statistic and squared prediction error SVE statistic and reduce missed detection rates. T2 statistic can be used to measure the variation di rectly along each KPC and analyze the detection performance as well as capture the most useful information in a process. With the calculation of the change rate of T2 statistic along each KPC, SKPCA selects the sensitive kernel principal components for process monitoring. A simulated simple system and Tennessee Eastman process are employed to demonstrate the efficiency of SKPCA on online monitoring. The results indicate that the monitoring performance is improved significantly.
基金the National Natural Science Foundation of China(61903352)China Postdoctoral Science Foundation(2020M671721)+4 种基金Zhejiang Province Natural Science Foundation of China(LQ19F030007)Natural Science Foundation of Jiangsu Province(BK20180594)Project of department of education of Zhejiang province(Y202044960)Project of Zhejiang Tongji Vocational College of Science and Technology(TRC1904)Foundation of Key Laboratory of Advanced Process Control for Light Industry(Jiangnan University),Ministry of Education,P.R.China,APCLI1803.
文摘Due to higher demands on product diversity,flexible shift between productions of different products in one equipment becomes a popular solution,resulting in existence of multiple operation modes in a single process.In order to handle such multi-mode process,a novel double-layer structure is proposed and the original data are decomposed into common and specific characteristics according to the relationship between variables among each mode.In addition,both low and high order information are considered in each layer.The common and specific information within each mode can be captured and separated into several subspaces according to the different order information.The performance of the proposed method is further validated through a numerical example and the Tennessee Eastman(TE)benchmark.Compared with previous methods,superiority of the proposed method is validated by the better monitoring results.
基金supported in part by the National Science Fund for Distinguished Young Scholars of China(62225303)the National Natural Science Fundation of China(62303039,62433004)+2 种基金the China Postdoctoral Science Foundation(BX20230034,2023M730190)the Fundamental Research Funds for the Central Universities(buctrc202201,QNTD2023-01)the High Performance Computing Platform,College of Information Science and Technology,Beijing University of Chemical Technology
文摘Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems,such as thermal power plants being studied in this work.Industrial processes are inherently dynamic and need to be monitored using dynamic algorithms.Mainstream dynamic algorithms rely on concatenating current measurement with past data.This work proposes a new,alternative dynamic process monitoring algorithm,using dot product feature analysis(DPFA).DPFA computes the dot product of consecutive samples,thus naturally capturing the process dynamics through temporal correlation.At the same time,DPFA's online computational complexity is lower than not just existing dynamic algorithms,but also classical static algorithms(e.g.,principal component analysis and slow feature analysis).The detectability of the new algorithm is analyzed for three types of faults typically seen in process systems:sensor bias,process fault and gain change fault.Through experiments with a numerical example and real data from a thermal power plant,the DPFA algorithm is shown to be superior to the state-of-the-art methods,in terms of better monitoring performance(fault detection rate and false alarm rate)and lower computational complexity.
基金financially supported by the National Natural Science Foundation of China(Grant No.52079150)Science and Technology Major Project of the Xizang Autonomous Region of China(XZ202201ZD0003G)Water Conservancy Technology Demonstration Project(SF-202404).
文摘This study aims to enhance the digital drilling process monitoring(DPM)or monitoring while drilling(MWD)technique,which is a widely recognized method in geological exploration for evaluating rock mass quality.First,robust displacement and torque measurement facilities for rotary-core drilling are discussed.The conventional cable encoder for displacement measurement is replaced with a magnetostrictive displacement sensor,which is more reliable in harsh field drilling environments.This enables the measurement of the bit position with an accuracy of<1 mm.Most importantly,this new instrument is proven to be successful in improving the detection of structural discontinuities with thicknesses>1 mm.In addition,by measuring the electric current of the driving motor,the torque applied to the bit is conveniently and accurately converted.These innovations ensure high-quality data collection for DPM practices.Second,two indices derived from DPM are proposed to quantitatively describe rock mass quality.The specific energy index(SEI)and specific penetration index(SPI)are based on the principles of energy conservation and Mohr-Coulomb failure criterion,respectively.Extensive field tests conducted in a dam grouting area confirm a linear relationship between the thrust force and penetration per rotation,and between the torque and penetration per rotation.The correlation ratios of the related regressions are typically>0.9.These two indices allow for the quantitative interpretation of DPM data into rock mechanics characteristics,such as uniaxial compressive strength,rock quality designation(RQD),and rock mass permeability,eliminating the need for subjective judgment normally involved in the currently used rock mass quality rating approaches.
基金supported by Open Research Fund of the Sichuan Institute of Xiamen University(Grant No.202401ZDB004)。
文摘Difficulties in the geometric and performance control of wire laser additive manufacturing have hindered its widespread application.In this study,an in situ process monitoring system that combines a machine vision-based interlayer height controller(IHC)and P-controller-based melt pool temperature controller(MTC)was developed to improve the vertical dimensional accuracy and mechanical properties of off-axis fine-wire laser-directed energy deposition(OAFW-LDED)for 316 L thin-walled parts.The IHC effectively mitigates external defect inheritance,while its synergy with the MTC ensures process stability,improving the vertical dimensional accuracy to±0.2 mm.Grain refinement was achieved by controlling the thermal input to optimize the thermal history and heat accumulation.A heterogeneous microstructure with alternating coarse and fine grains was observed and intergranular thermal cracking was suppressed.The yield and tensile strengths increased from 262 to 416 MPa to 313 and 516 MPa,respectively,with improved consistency in the yield strength between the top and bottom sections.However,excessive laser heat input caused interlayer cracks.Conversely,increasing the heat input through substrate preheating did not induce additional cracks and improved the overall hardness consistency of the thin-walled samples.Therefore,this study proposes a new formability control strategy for OAFW-LDEDs of thin-walled parts.
基金supported by grants from the Research Grant Council of the Hong Kong Special Administrative Region,China(Grant No.HKU 7137/03E)the National Natural Science Foundation of China(Grant No.41977248)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB10030100).
文摘The increasing demand for unconventional oil and gas resources,especially oil shale,has highlighted the urgent need to develop rapid and accurate strata characterization methods.This paper is the first case and examines the drilling process monitoring(DPM)method as a digital,accurate,cost-effective method to characterize oil shale reservoirs in the Ordos Basin,China.The digital DPM method provides real-time in situ testing of the relative variation in rock mechanical strength along the drill bit depth.Furthermore,it can give a refined rock quality designation based on the DPM zoning result(RQD(V_(DPM)))and a strength-grade characterization at the site.Oil shale has high heterogeneity and low strata strength.The digital results are further compared and verified with manual logging,cored samples,and digital panoramic borehole cameras.The findings highlight the innovative potential of the DPM method in identifying the zones of oil shale reservoir along the drill bit depth.The digital results provide a better understanding of the oil shale in Tongchuan and the potential for future oil shale exploration in other regions.
基金The support provided by the National Natural Science Foundation of China(Grant No.42277160)the Natural Science Foundation of Hubei Province(Grant No.2021CFA081)the Fundamental Research Funds for the Central Universities(Grant No.2042023kf0210)is gratefully acknowledged.
文摘The evaluation of rock mass quality and its mechanical properties is crucial for tunnel construction.The basic quality(BQ)method is the national standard for rock mass classification in China,with the BQ value determined by the uniaxial compressive strength(UCS)and the integrity index(Kv).However,traditional rock mechanics testing methods have inherent limitations,which complicate the rapid evaluation of rock mass quality at tunnel sites.Digital drilling process monitoring(DPM)offers a novel approach for evaluating rock mass quality and its mechanical properties.A hydraulic rotary drilling rig,equipped with the DPM system,was used to conduct digital drilling tests at the tunnel face.The DPM data for the net drilling process and each sub-process were then analyzed.The correlations between DPM parameter indices and rock mechanical parameters were investigated.Finally,the rock mass quality and its mechanical properties along three boreholes were evaluated.The results indicate that drilling speed in the linear zone(V_(DPM))is quantitatively correlated with rock UCS.Higher UCS values of the drilled rocks correspond to lower V_(DPM) values of the drilling rig.The variability in specific energy is associated with structural disturbances within the rock mass.There is an approximately linear relationship between the standard deviation of normalized specific energy and rock mass K_(v) across the three boreholes.The rock mass quality along drilling depth generally ranges from good(Ⅰ-Ⅱ)to poor(Ⅲ-Ⅴ).This digitalization method provides more detailed information for tunnel stability analysis and design optimization than geological survey data.
基金supported by the Deputyship for Research and Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number(0226-1443-S).
文摘Environmental protection requires identifying,investigating,and raising awareness about safeguarding nature from the harmful effects of both anthropogenic and natural events.This process of environmental protection is essential for maintaining human well-being.In this context,it is critical to monitor and safeguard the personal environment,which includes maintaining a healthy diet and ensuring plant safety.Living in a balanced environment and ensuring the safety of plants for green spaces and a healthy diet require controlling the nature and quality of the soil in our environment.To ensure soil quality,it is imperative to monitor and assess the levels of various soil parameters.Therefore,an Optimized Reduced Kernel Partial Least Squares(ORKPLS)method is proposed to monitor and control soil parameters.This approach is designed to detect increases or deviations in soil parameter quantities.A Tabu search approach was used to select the appropriate kernel parameter.Subsequently,soil analyses were conducted to evaluate the performance of the developed techniques.The simulation results were analyzed and compared.Through this study,deficiencies or exceedances in soil parameter quantities can be identified.The proposed method involves determining whether each soil parameter falls within a normal range.This allows for the assessment of soil parameter conditions based on the principle of fault detection.
基金The National Natural Science Foundation of China(No60504033)
文摘A novel online process monitoring and fault diagnosis method of condenser based on kernel principle component analysis （KPCA） and Fisher discriminant analysis （FDA） is presented. The basic idea of this method is： First map data from the original space into high-dimensional feature space via nonlinear kernel function and then extract optimal feature vector and discriminant vector in feature space and calculate the Euclidean distance between feature vectors to perform process monitoring. Similar degree between the present discriminant vector and optimal discriminant vector of fault in historical dataset is used for diagnosis. The proposed method can effectively capture the nonlinear relationship among process variables. Simulating results of the turbo generator＇s fault data set prove that the proposed method is effective.
基金Sponsored by the National Natural Science Foundation of China[grant number 12571305]the Natural Science Foundation of Shanghai[grant number 25ZR1401113].
文摘Traditional multivariate parametric control charts often perform inadequately in detecting shifts in the covariance matrix when the data deviate from normality.In this paper,we propose a multivariate nonparametric exponentially weighted moving average(SGLGEWMA)control chart,incorporating a Sparse Group Lasso penalty,which is capable of detecting shifts in the covariance matrix across a wide range of data types,including discrete,continuous,and mixed distributions.The proposed approach projects multivariate data into a Euclidean space and then computes an approximate Alt’s likelihood ratio,regularized via the Sparse Group Lasso.The resulting EWMA statistic monitors process shifts.Monte Carlo simulations demonstrate that SGLGEWMA outperforms both the Lasso-based LGShewhart and the Ridge-based RGEWMA control charts under various distributions,with enhanced efficacy in high-dimensional scenarios.Sensitivity analyses are performed on the tuning parameters(λ_(1),λ_(2))and smoothing parameterρ,to evaluate their impact on monitoring performance.Additionally,a simulation study and an illustrative example involving covariance monitoring in wafer semiconductor manufacturing are presented to demonstrate the practical application of the proposed chart.Empirical results confirm that the proposed control chart promptly identifies abnormal fluctuations and issues timely alerts,highlighting both its theoretical significance and practical utility.
基金Supported by the National Natural Science Foundation of China （No.60574047） and the Doctorate Foundation of the State Education Ministry of China （No.20050335018）.
文摘Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the two methods is that the components of PCA are still dependent while ICA has no orthogonality constraint and its latentvariables are independent. Process monitoring with PCA often supposes that process data or principal components is Gaussian distribution. However, this kind of constraint cannot be satisfied by several practical processes. To ex-tend the use of PCA, a nonparametric method is added to PCA to overcome the difficulty, and kernel density estimation （KDE） is rather a good choice. Though ICA is based on non-Gaussian distribution intormation, .KDE can help in the close monitoring of the data. Methods, such as PCA, ICA, PCA.with .KDE（KPCA）, and ICA with KDE,（KICA）, are demonstrated and. compared by applying them to a practical industnal Spheripol craft polypropylene catalyzer reactor instead of a laboratory emulator.
文摘In the past decades, on-line monitoring of batch processes using multi-way independent component analysis （MICA） has received considerable attention in both academia and industry. This paper focuses on two troublesome issues concerning selecting dominant independent components without a standard criterion and deter- mining the control limits of monitoring statistics in the presence of non-Gaussian distribution. To optimize the number of key independent components~ we introctuce-anoveiconcept of-system-cleviation, which is ab^e＇io＇evalu[ ate the reconstructed observations with different independent components. The monitored statistics arc transformed to Gaussian distribution data by means of Box-Cox transformation, which helps readily determine the control limits. The proposed method is applied to on-line monitoring of a fed-hatch penicillin fermentation simulator, and the ex- _perimental results indicate the advantages of the improved MICA monitoring compared to the conventional methods.
基金Supported by the National High-Tech Development Program of China(No.863-511-920-011,2001AA411230).
文摘Multivariate statistical process monitoring and control (MSPM&C) methods for chemical process monitoring with statistical projection techniques such as principal component analysis (PCA) and partial least squares (PLS) are surveyed in this paper. The four-step procedure of performing MSPM&C for chemical process, modeling of processes, detecting abnormal events or faults, identifying the variable(s) responsible for the faults and diagnosing the source cause for the abnormal behavior, is analyzed. Several main research directions of MSPM&C reported in the literature are discussed, such as multi-way principal component analysis (MPCA) for batch process, statistical monitoring and control for nonlinear process, dynamic PCA and dynamic PLS, and on-line quality control by inferential models. Industrial applications of MSPM&C to several typical chemical processes, such as chemical reactor, distillation column, polymerization process, petroleum refinery units, are summarized. Finally, some concluding remarks and future considerations are made.
基金Department for the technical and administrative support and the financial support from the Yayasan UTP grant(Cost centre:015LC0-132).
文摘Process monitoring techniques are of paramount importance in the chemical industry to improve both the product quality and plant safety.Small or incipient irregularities may lead to severe degradation in complex chemical processes,and the conventional process monitoring techniques cannot detect these irregularities.In this study to improve the performance of monitoring,an online multiscale fault detection approach is proposed by integrating multiscale principal component analysis(MSPCA) with cumulative sum(CUSUM) and exponentially weighted moving average(EWMA) control charts.The new Hotelling's T~2 and square prediction error(SPE) based fault detection indices are proposed to detect the incipient irregularities in the process data.The performance of the proposed fault detection methods was tested for simulated data obtained from the CSTR system and compared to that of conventional PCA and MSPCA based methods.The results demonstrate that the proposed EWMA based MSPCA fault detection method was successful in detecting the faults.Moreover,a comparative study shows that the SPEEWMA monitoring index exhibits a better performance with lower values of missed detections ranging from 0% to 0.80% and false alarms ranging from 0% to 21.20%.
基金Supported by the National High-tech Program of China (No. 2001 AA413110).
文摘Multi-way principal component analysis (MPCA) had been successfully applied to monitoring the batch and semi-batch process in most chemical industry. An improved MPCA approach, step-by-step adaptive MPCA (SAMPCA), using the process variable trajectories to monitoring the batch process is presented in this paper. It does not need to estimate or fill in the unknown part of the process variable trajectory deviation from the current time until the end. The approach is based on a MPCA method that processes the data in a sequential and adaptive manner. The adaptive rate is easily controlled through a forgetting factor that controls the weight of past data in a summation. This algorithm is used to evaluate the industrial streptomycin fermentation process data and is compared with the traditional MPCA. The results show that the method is more advantageous than MPCA, especially when monitoring multi-stage batch process where the latent vector structure can change at several points during the batch.
基金Supported by the National Natural Science Foundation of China (61074079)Shanghai Leading Academic Discipline Project (B054)
文摘For complex industrial processes with multiple operational conditions, it is important to develop effective monitoring algorithms to ensure the safety of production processes. This paper proposes a novel monitoring strategy based on fuzzy C-means. The high dimensional historical data are transferred to a low dimensional subspace spanned by locality preserving projection. Then the scores in the novel subspace are classified into several overlapped clusters, each representing an operational mode. The distance statistics of each cluster are integrated though the membership values into a novel BID (Bayesian inference distance) monitoring index. The efficiency and effectiveness of the proposed method are validated though the Tennessee Eastman benchmark process.
基金supported by National Key R&D Program of China(Smart process control technology for aluminum&copper strip based on industrial big data)(2017YFB0306405)。
文摘For the complex batch process with characteristics of unequal batch data length,a novel data-driven batch process monitoring method is proposed based on mixed data features analysis and multi-way kernel entropy component analysis(MDFA-MKECA)in this paper.Combining the mechanistic knowledge,different mixed data features of each batch including statistical and thermodynamics entropy features,are extracted to finish data pre-processing.After that,MKECA is applied to reduce data dimensionality and finally establish a monitoring model.The proposed method is applied to a reheating furnace industry process,and the experimental results demonstrate that the MDFA-MKECA method can reduce the calculated amount and effectively provide on-line monitoring of the batch process.
