Changes In Process Characteristics Research Articles

Understanding tool chip interaction through experimental and numerical analysis during vibration assisted turning of AISI D3 steel

Vibration Assisted Turning (VAT) is a hybrid machining process where the material is machined with the help of a tool vibrating at ultrasonic frequency. VAT results in significant changes in process characteristics compared to conventional machining, like reducing the machining forces and tool wear. The chips produced during the machining operation can provide valuable insight into the process characteristics like machining zone temperature, friction at the tool-chip interface and chip load that primarily alter the process performance. One can understand and have a better control on the machining process performance by studying the formation of these chips and the tool-chip interaction. The work presents an experimental and numerical study to analyze the chip formation during VAT while machining AISI D3 steel. The chips formed while machining at different vibration amplitudes were observed to be of different colors, widths, and thicknesses. These were found to correlate to the forces generated and the surface integrity produced. A decrease in the chip width and thickness was observed with an increase in the amplitude that helps to reduce the chip load and hence forces. Also, the temperature at the machining zone increased with an increase in amplitude as seen from different color of chips produced and carbon content of the chip. The numerical model, developed to analyze the effect of the vibration amplitude on the contact pressure at the chip-tool interface, showed that the average contact pressure reduced upon applying ultrasonic vibration to the tool, thereby reducing the coefficient of friction and frictional forces. Also, with increase in vibration amplitude, the coefficient of friction was found increasing but it still remained lower than that in conventional turning. The study would help to understand the reduction the overall machining forces and chip morphology and thereby to have a better control on the process performance.

Online-Dynamic-Clustering-Based Soft Sensor for Industrial Semi-Supervised Data Streams.

In the era of big data, industrial process data are often generated rapidly in the form of streams. Thus, how to process such sequential and high-speed stream data in real time and provide critical quality variable predictions has become a critical issue for facilitating efficient process control and monitoring in the process industry. Traditionally, soft sensor models are usually built through offline batch learning, which remain unchanged during the online implementation phase. Once the process state changes, soft sensors built from historical data cannot provide accurate predictions. In practice, industrial process data streams often exhibit characteristics such as nonlinearity, time-varying behavior, and label scarcity, which pose great challenges for building high-performance soft sensor models. To address this issue, an online-dynamic-clustering-based soft sensor (ODCSS) is proposed for industrial semi-supervised data streams. The method achieves automatic generation and update of clusters and samples deletion through online dynamic clustering, thus enabling online dynamic identification of process states. Meanwhile, selective ensemble learning and just-in-time learning (JITL) are employed through an adaptive switching prediction strategy, which enables dealing with gradual and abrupt changes in process characteristics and thus alleviates model performance degradation caused by concept drift. In addition, semi-supervised learning is introduced to exploit the information of unlabeled samples and obtain high-confidence pseudo-labeled samples to expand the labeled training set. The proposed method can effectively deal with nonlinearity, time-variability, and label scarcity issues in the process data stream environment and thus enable reliable target variable predictions. The application results from two case studies show that the proposed ODCSS soft sensor approach is superior to conventional soft sensors in a semi-supervised data stream environment.

Guest Editorial Special Issue on Emerging Computational Intelligence Techniques for Decision Making With Big Data in Uncertain Environments

The papers in this special section focus on emerging computational intelligent techniques for decision making with Big Data in uncertain environments. Decision making in a big-data environment poses many challenges because of the high dimensional, heterogeneous, complex, unstructured, and unpredictable characteristics of the data which often suffer from different kinds of uncertainty. The uncertainty in the data may arise due to many factors including missing values, imprecise measurements, changes in process characteristics during the data generation period, lack of appropriate monitoring of data measurement process to name a few. Internet-of-Things (IoT) systems usually generate a large amount of unstructured and heterogeneous data demanding specialized techniques for data analytics. Thus, decision making in such an environment poses significant challenges and often demands new and innovative design techniques and algorithms for decision making.

Ensemble just-in-time model based on Gaussian process dynamical models for nonlinear and dynamic processes

Process data have a number of characteristics, such as noise, nonlinearity, process dynamics, and autocorrelation. Ideally, adaptive soft sensors would be used to solve model degradation problems resulting from changes in process characteristics. However, it is necessary to optimize the hyperparameters for each model and, depending on the state of the process, the optimal hyperparameters will change. In this study, we focus on a Gaussian process dynamical model (GPDM), a dimension-reduction method that considers all of the data characteristics. We combine a just-in-time (JIT) model and ensemble learning, and then predict y-values with multiple JIT models that have different sets of hyperparameters. Each JIT model is constructed using latent variables obtained by the GPDM. The weights of the JIT models are determined based on Bayes’ theorem in consideration of their predictive ability. Analysis of two industrial datasets confirms that the proposed model is more accurate than existing approaches.

Adaptive JIT-Lasso modeling for online application of near infrared spectroscopy

Near infrared (NIR) spectroscopy has been widely employed as a non-invasive analytical tool in industry. However, most NIR model are built offline which cannot address changes in process characteristics as well as nonlinearity. To solve this problem, an adaptive JIT-Lasso algorithm was proposed by merging the least absolute shrinkage and the selection operator (Lasso) algorithm into just-in-time (JIT) learning. A time-space similarity measure criterion that combined temporal relevance and spatial relevance was used to further improve the performance of the JIT-Lasso algorithm. This solved both the space nonlinearity and the time-varying issue of the process simultaneously. The proposed model updating approach not only solved the nonlinear and the time-varying issues based on JIT learning framework, but also reduced the computational complexity and improved the model interpretability through Lasso. The effectiveness of the method was demonstrated on a spectroscopic dataset from an industrial petroleum desalination process. Compared with traditional partial least squares, kernel partial least square, locally weighted partial least squares, locally weighted kernel partial least squares,the proposed method achieves better performance.

A Two-step Parallel Phase Partition Algorithm for Monitoring Multiphase Batch Processes with Limited Batches

For multiphase batch processes, dividing the whole batch process into different phases by time-varying underlying characteristics could simplify model complexity without much loss of precision. The conventional step-wise sequential phase partition (SSPP) algorithm divides the batch process rely on the previous partition phase, which easily results in error accumulation. Besides, it is hardly applied to batch processes with limited training batches. In this paper, a parallel phase partition algorithm with limited batches is proposed for addressing those issues. By analyzing the contextual information of each time-slice, the batch process can be roughly divided using the time-varying characteristics. Based on the division result, parallel phase partition method is conducted to avoid error accumulation and connect the division result with monitoring system. To better capture the changes of process characteristics, we post-process the division result and update the boundaries between major phases and transition patterns. After phase and transition partition, different statistical models are developed so that the online monitoring can be executed. Experiments of process monitor are designed with an injection modeling process, and experimental results illustrate the process understanding ability and online monitoring performance of our proposed method.

データ駆動型アプローチによる製造技術強化 : いかにプロセス特性変化に対応するか( データ駆動型アプローチの新展開)

データ駆動型アプローチによる製造技術強化 : いかにプロセス特性変化に対応するか( データ駆動型アプローチの新展開)

Process Understanding in Freeze-Drying Cycle Development: Applications for Through-Vial Impedance Spectroscopy (TVIS) in Mini-pilot Studies

Purpose The freeze-drying cycle comprises three stages: (1) freezing, to form ice and to crystallise out any solutes with a propensity to crystallise, (2) primary drying to remove the ice phase by sublimation and (3) secondary drying to remove the remaining unfrozen water which is bound to the remaining matrix of crystalline and amorphous solids. Given the impact of scale on the process outcomes, any freeze-drying cycle developed based on mini-pilot studies will inevitably require measurement technologies for characterising each stage of the cycle at each scale of the process. However, there are inherent challenges in the development of reliable mini-piloting studies, with the first being the fact that no single PAT technology for freeze drying may be implemented across all levels of scale, and the second being the inherent changes in process characteristics (process parameters that result from scale-up).

Sparse Sample Regression Based Just-In-Time Modeling (SSR-JIT): Beyond Locally Weighted Approach

In the present work, a new method for just-in-time (JIT) modeling is proposed. To develop virtual sensors or soft-sensors that can cope with changes in process characteristics as well as nonlinearity, JIT modeling such as locally weighted regression (LWR) and locally weighted partial least squares (LW-PLS) has been investigated and successfully used in various industries. The conventional JIT modeling methods predict output variables by constructing a local model by using past samples located in the neighborhood around the new target sample (query) every time when the output prediction is required; the modeling samples are selected or weighted according to the similarity between the samples and the query. The similarity is usually determined on the basis of the distance from the query. However, the use of distance does not assure the high prediction accuracy. To overcome this limitation of the conventional JIT methods, the proposed method selects past samples that are useful for constructing an accurate local model by using elastic net, which builds a sparse regression model to estimate the query, and uses the derived regression coefficients to evaluate the similarity for conducting LW-PLS. This sparse sample regression based just-in-time modeling (SSR-JIT) has a potential for surpassing the conventional distance-based JIT modeling. In fact, it was demonstrated that SSR-JIT outperformed LW-PLS in the prediction accuracy through two case studies with real industrial data.

Adaptive Virtual Metrology Design for Semiconductor Dry Etching Process Through Locally Weighted Partial Least Squares

In semiconductor manufacturing processes, virtual metrology (VM) has been investigated as a promising tool to predict important characteristics of products. Although partial least squares (PLS) is a well-known modeling technique that can cope with collinearity and therefore applied to construction of VM, its prediction performance deteriorates due to changes in process characteristics. In particular, maintenance of equipment strongly affects the process characteristics and the prediction performance. In this paper, VM was developed by using locally weighted PLS (LW-PLS), which is a type of just-in-time modeling technique, and it was used to predict the etching conversion differential of an actual dry etching process. The industrial application results have shown that the developed VM based on LW-PLS is superior to the conventional VM based on the sequential update model and artificial neural network model. In particular, it has been confirmed that the LW-PLS-based VM can keep its high prediction performance even after the maintenance, i.e., replacement of parts.

Complex batch processes quality prediction using non-Gaussian dissimilarity measure based just-in-time learning model

In modern batch processes, soft sensors have been widely used for estimating quality variables. However, they do not show superior prediction performance due to the self-limitations of these methods and the unique characteristics of batch processes such as time-varying, nonlinearity, non-Gaussianity, multi-phases and batch-to-batch variations. To cope with these issues, a novel non-Gaussian dissimilarity measure based just-in-time learning (JITL) soft sensor is developed in this paper. Unlike the traditional JITL model which uses the distance-based dissimilarity measure for local modeling, the proposed method uses non-Gaussian dissimilarity measure to evaluate the statistical dependency of the extracted independent components to construct the local model, which can well capture the non-Gaussian features in the process data. Furthermore, a novel relevant samples search strategy is introduced into the JITL framework for local modeling, which not only searches the relevant samples along the direction of time axis but also along the direction of batch-to-batch. The proposed search strategy can guarantee the current query sample and the local modeling data belong to the same phase duration and have the smallest process trajectory variations. Hence, the proposed soft sensor is suitable for uneven-phase and batch-to-batch variations batch processes. Meanwhile, the proposed method can well cope with the changes in process characteristics as well as nonlinearity. The effectiveness of the proposed method is verified on the fed-batch Penicillin Fermentation process.

Process Parameter Optimization based on LW-PLS in Pharmaceutical Granulation Process

A process optimization method based on partial least squares (PLS) has been used in pharmaceutical processes. However, its applicability and performance are limited because PLS cannot cope with nonlinearity and changes in process characteristics. In this research, a new process optimization method based on locally weighted PLS (LW-PLS) is proposed. To solve a nonlinear optimization problem based on LW-PLS, in which any global model is not constructed, self-adaptive differential evolution (jDE) is adopted. The validity of the proposed method is demonstrated through a numerical example and an industrial case study of a pharmaceutical granulation process.

Adaptive Gaussian Mixture Model-Based Relevant Sample Selection for JITL Soft Sensor Development

Just-in-time learning (JITL) has recently been used for online soft sensor modeling. Unlike traditional global approaches, the JITL-based method employs a local model built from historical samples similar to a query sample so that both nonlinearities and changes in process characteristics can be handled well. A key issue in JITL is to establish a suitable similarity criterion for selecting relevant samples. Conventional JITL methods, which use distance-based similarity measures for local modeling, can be inappropriate for many industrial processes exhibiting time-varying and non-Gaussian behaviors. In this article, a GMM-based similarity measure is proposed to improve the prediction accuracy of a JITL soft sensor. By taking the non-Gaussianity of the process data and the characteristics of the query sample into account, a more suitable similarity criterion is defined for sample selection of a JITL soft sensor, and better modeling performance can be achieved. Case studies involving a numerical example and ...

A Quality-Relevant Sequential Phase Partition Approach for Regression Modeling and Quality Prediction Analysis in Manufacturing Processes

Competition and demand for consistent and high-quality product have spurred the development of quality prediction methods for industrial manufacturing processes. Mul- tiplicity of phases is, in general, common nature of many batch manufacturing processes. Considering that different phases may have different effects on qualities, one of the key issues is how to partition the whole batch process into multiple phases. In the present work, an automatic quality-relevant step-wise sequential phase partition (QSSPP) algorithm is developed for phase-based regression modeling and quality prediction. It considers the time sequence of operation phases and can capture the time-varying quality prediction relationships. Using this algorithm, phases are separated in order from quality-relevant perspective, revealing different quality prediction relationships. The phase-based re- gression system is set up for online quality prediction and the online prediction results are quantitatively evaluated for each phase. The feasibility and performance of the proposed algorithm are illustrated by an important manufacturing process, injection molding. Note to Practitioners—This paper was motivated by competition and demand for consistent and high-quality product for indus- trial manufacturing processes with multiphase characteristics. Industrial experts have noted that events taking place in different phases may have different impacts on the final product yield and quality. Phase-based quality prediction has drawn their attention by providing quality information before the end of processes. This paper suggests an automatic sequential phase partition algorithm for phase-based regression modeling and quality prediction which can identify phases in sequence from the quality-relevant per- spective. The division result is easy to read and does not need a heavy postprocessing as what is done for clustering-based result. The phase information is identified in order by directly relating changes of process characteristics with their influence on quality prediction performance. More accurate regression models and online quality prediction results can thus be readily obtained. Preliminary experiments suggest that this approach is feasible but it has not yet been incorporated into a quality control system nor tested in practical industrial production. In future research,

Adaptive soft sensor based on online support vector regression and Bayesian ensemble learning for various states in chemical plants

A soft sensor predicts the values of some process variable y that is difficult to measure. To maintain the predictive ability of a soft sensor model, adaptation mechanisms are applied to soft sensors. However, even these adaptive soft sensors cannot predict the y-values of various process states in chemical plants, and it is difficult to ensure the predictive ability of such models on a long-term basis. Therefore, we propose a method that combines online support vector regression (OSVR) with an ensemble learning system to adapt to nonlinear and time-varying changes in process characteristics and various process states in a plant. Several OSVR models, each of which has an adaptation mechanism and is updated with new data, predict y-values. A final predicted y-value is calculated based on those predicted y-values and Bayes' rule. We analyze a numerical dataset and two real industrial datasets, and demonstrate the superiority of the proposed method.

An iterative within-phase relative analysis algorithm for relative sub-phase modeling and process monitoring

For multiphase batch processes, sub-phase modeling methods assumed that the underlying process characteristics stay similar within the same phase which thus can be represented by one unified phase model. However, despite the similarity, process characteristics may also be different more or less within the same phase, revealing a certain degree of within-phase dissimilarity. How to distinguish within-phase similarity and dissimilarity and separately model them for online monitoring are important questions, which, however, have not be addressed yet. In the present work, an iterative within-phase relative analysis algorithm is proposed to handle this problem. Instead of arbitrary similarity assumption, relative changes of process characteristics along time direction are analyzed for time-slices within the same phase. Thus, two systematic subspaces are separated at each time, revealing within-phase similar characteristics and within-phase dissimilar characteristics respectively. Only the within-phase similar part can be described by a unified phase model. In contrast, the within-phase dissimilar part reflects the time-varying characteristics even in the same phase and thus has to be described by different models. For online monitoring, different types of variations can be supervised respectively so that the changes of process variations can be more specifically tracked, providing reliable fault detection performance as well as enhanced process understanding. It is illustrated with a typical multiphase batch process.

Quality Quandaries: A Stepwise Approach for Setting Up a Robust Shewhart Location Control Chart

Shewhart control charts are extensively used in practice to monitor changes in process characteristics from the in-control state. There are many types of control chart applications, ranging from ch...

Quality‐relevant fault diagnosis with concurrent phase partition and analysis of relative changes for multiphase batch processes

Multiplicity of phases as indicated by changes of process characteristics is an inherent nature of many batch processes for both normal and fault cases. To more efficiently perform online fault diagnosis via reconstruction for multiphase batch processes, the phase nature and the relationship between normal and fault cases within each phase should be deeply addressed. This article proposes a quality‐relevant fault diagnosis strategy with concurrent phase partition and analysis of relative changes for multiphase batch processes. First, a concurrent phase partition algorithm is developed. The basic idea is to track the changes of process characteristics at normal and fault statuses jointly so that multiple sequential modeling phases are identified simultaneously for both normal and fault cases. Then, the relative changes from the normal status to each fault case are analyzed in each phase to reveal the specific fault effects more efficiently. The fault effects are decomposed in two different monitoring subspaces, principal subspace, and residual subspace, by capturing their different roles in removing out‐of‐control signals. The significant increases relative to the normal case are judged to be responsible for the concerned alarm monitoring statistics in each phase. The others are composed of general variations that are deemed to still follow normal rules and thus insignificant to remove alarm monitoring statistics. Those alarm‐responsible fault deviations are then used to develop reconstruction models which can more efficiently recover the fault‐free part for online fault diagnosis. The proposed algorithm is illustrated with a typical multiphase batch process with one normal case and three fault cases. © 2014 American Institute of Chemical Engineers AIChE J, 60: 2048–2062, 2014

A Step-wise sequential phase partition algorithm with limited batches for statistical modeling and online monitoring of multiphase batch processes

For batch processes, sufficient batches are in general required for statistical modeling and process monitoring. However, sometimes, it is difficult and may be impractical to conduct multiple cycles and wait until enough batches are available. Thus, how to derive reliable process information based on limited batches has been an important question. Starting from limited modeling batches, this article proposes a phase partition and process monitoring strategy for multiphase batch processes. First, a step-wise sequential phase partition algorithm is developed with limited batches where a generalized time-slice is constructed by combining several consecutive time-slices within a short time region to analyze changes of process characteristics. Multiple phases are thus identified in sequence along time direction which are described by different phase models. The feasibility and performance of the proposed method for online process monitoring are illustrated with experimental data from a typical multiphase batch process.

Application of online support vector regression for soft sensors

Soft sensors have been widely used in chemical plants to estimate process variables that are difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes in state of chemical plants. Characteristics of adaptive soft sensor models such as moving window models, just‐in‐time models and time difference models were previously discussed. The predictive accuracy of any traditional models decreases when sudden changes in processes occur. Therefore, a new soft sensor method based on online support vector regression (SVR) and the time variable was developed for constructing soft sensor models adaptive to rapid changes of relationships among process variables. A nonlinear SVR model with the time variable is updated with the most recent data. The proposed method was applied to simulation data and real industrial data, and achieved higher predictive accuracy than traditional ones even when time‐varying changes in process characteristics happen. © 2013 American Institute of Chemical Engineers AIChE J 60: 600–612, 2014