No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Data-driven modeling of semi-batch manufacturing: a rubber compounding test case
... It can be explained as ZDM paradigm builds on SPC concepts, where the process is central with respect to other system components and resources. There also seems to be a trend towards more productcentricity in ZDM research (e.g., Krammer et al., 2017;Alfaro-Isac et al., 2019;Aal et al., 2020). Though the people-centric component of ZDM has begun to appear in the extant research, most of the examples seem to be rather coincidental, often coming secondary to a focus on the process dimension (e.g., Mahmud et al., 2015;Siew et al., 2016;Kang et al., 2019;Steringer et al., 2019;Wang et al., 2019). ...
Zero Defect Manufacturing is a disruptive concept that has the potential to entirely reshape the manufacturing ideology. Building on the same quality management philosophy that underpins both lean production and Six Sigma, the Zero Defect Manufacturing paradigm has in recent years developed significantly, given the onset of Industry 4.0 and the increasing maturity of its digital technologies. In this paper, we review contemporary advances in Zero Defect Manufacturing using structured literature review. We explore emergent themes and present important directions for future development in this continuously emerging field of research and practice. We highlight two specific Zero Defect Manufacturing strategy types: defect prevention, and defect compensation; as well as identify two important themes for future ZDM research, namely advancing ZDM research (particularly with a view to progressing from zero-defect processes to zero-waste value chain strategies) and overcoming the global application challenges of ZDM (with emphasis on cyber-security and the extension of defect prevention and compensation strategies to less explored manufacturing processes).
This paper presents a smart manufacturing analytics application for semi-continuous manufacturing process with a use case, and provides some ideas for widespread implementation of such applications. With the concurrent efforts in process modelling, data collection and online process control, process performance has been continually improving over the years. In a modern production canter, there are hundreds of sensors continuously collecting process information along with the product quality information available post-process. These data contain vital process insights yet organization, filtering and contextualization challenges prohibit the widespread use of the data to gain valuable insights about the process. This paper presents such a use case by discussing required elements for a complete advanced analytic application with examples. The paper concludes with thoughts on wide-spread deployment of such techniques
The advances in the internet technology, internet of things, cloud computing, big data, and artificial intelligence have profoundly impacted manufacturing. The volume of data collected in manufacturing is growing. Big data offers a tremendous opportunity in the transformation of today’s manufacturing paradigm to smart manufacturing. Big data empowers companies to adopt data-driven strategies to become more competitive. In this paper, the role of big data in supporting smart manufacturing is discussed. A historical perspective to data lifecycle in manufacturing is overviewed. The big data perspective is supported by a conceptual framework proposed in the paper. Typical application scenarios of the proposed framework are outlined.
Smart manufacturing refers to using advanced data analytics to complement physical science for improving system performance and decision making. With the widespread deployment of sensors and Internet of Things, there is an increasing need of handling big manufacturing data characterized by high volume, high velocity, and high variety. Deep learning provides advanced analytics tools for processing and analysing big manufacturing data. This paper presents a comprehensive survey of commonly used deep learning algorithms and discusses their applications toward making manufacturing “smart”. The evolvement of deep learning technologies and their advantages over traditional machine learning are firstly discussed. Subsequently, computational methods based on deep learning are presented specially aim to improve system performance in manufacturing. Several representative deep learning models are comparably discussed. Finally, emerging topics of research on deep learning are highlighted, and future trends and challenges associated with deep learning for smart manufacturing are summarized.
A batch process is characterized by the repetition of time-varying operations of finite duration. Due to the repetition, there are two independent "time" variables, namely, the run time during a batch and the batch index. Accordingly, the control and optimization objectives can be defined for a given batch or over several batches. This chapter describes the various control and optimization strategies available for the operation of batch processes. These include online and run-to-run control on the one hand, and repeated numerical optimization and optimizing control on the other. Several case studies are presented to illustrate the various approaches.
In many data sets, there are only hundreds or fewer samples but thousands of features. The relatively small number of samples in high dimensional data results in modest classification performance and feature selection instability. In order to deal with the curse of dimensionality, we propose to investigate research on the effect of integrating background knowledge about some dimensions known to be more relevant, as a means of directing the feature selection process. We propose extensions of three feature selection techniques, two filters and a wrapper, by incorporating prior knowledge in the search procedure of the best features. We study the effect of these extensions on the classification performance and the stability of the feature selection. We experimentally test and compare our proposed approaches with their original versions, which do not integrate prior knowledge, over three high-dimensional datasets. The results show that our proposed techniques outperform other methods in terms of stability of feature selection but also in classification performance in most cases.
Scikit-learn is a Python module integrating a wide range of state-of-the-art
machine learning algorithms for medium-scale supervised and unsupervised
problems. This package focuses on bringing machine learning to non-specialists
using a general-purpose high-level language. Emphasis is put on ease of use,
performance, documentation, and API consistency. It has minimal dependencies
and is distributed under the simplified BSD license, encouraging its use in
both academic and commercial settings. Source code, binaries, and documentation
can be downloaded from http://scikit-learn.sourceforge.net.
Dynamic optimization of batch processes has attracted more attention in recent years since, in the face of growing competition, it is a natural choice for reducing production costs, improving product quality, and meeting safety requirements and environmental regulations. Since the models currently available in industry are poor and carry a large amount of uncertainty, standard model-based optimization techniques are by and large ineffective, and optimization methods need to rely more on measurements. In this paper, various measurement-based optimization strategies reported in the literature are classified. A new framework is also presented, where important characteristics of the optimal solution that are invariant under uncertainty are identified and serve as references to a feedback control scheme. Thus, optimality is achieved by tracking with no numerical optimization required on-line. When only batch-end measurements are available, the proposed method leads naturally to an efficient batch-to-batch optimization scheme. The approach is illustrated via simulation of a semi-batch reactor in the presence of uncertainty.
An important predictive maintenance task in modern production systems is to predict the quality of products in order to be able to intervene at an early stage to avoid faults and waste. Here, we address the prediction of the most important quality criteria in micro-fluidics chips: the flatness and critical size of the chips (in the form of RMSE values) and several transmission characteristics. Due to semi-manual inspection, these quality criteria are typically measured only intermittently. This leads to a high-dimensional batch process modeling problem with the goal of predicting chip quality based on the trends in these process values (time series). We apply time-series based transformation for dimension reduction to the lagged time-series space using of partial least squares (PLS), and combine this with a generalized form of Takagi–Sugeno(TS) fuzzy systems to obtain a non-linear PLS forecast model (termed as PLS-fuzzy). The rule consequent functions are robustly estimated by a weighted regularization scheme based on the idea of the elastic net approach. To address particular system dynamics over time, we propose dynamic updating of the non-linear PLS-fuzzy models using new on-line time-series data, with the options 1.) adapt and evolve the rule base on the fly, 2.) smoothly down-weight older samples to increase flexibility of the fuzzy models, and 3.) update the PLS space by incrementally adapting the loading vectors, where processing is achieved in a single-pass stream mining manner. We call our method IPLS-GEFS (incremental PLS combined with generalized evolving fuzzy systems). We applied our predictive modeling approach to data from on-line microfluidic chip production over a time period of about 6 months (July to December 2016). The results show that there is significant non-linearity in the predictive modeling problem, as the non-linear PLS-fuzzy modeling approach significantly outperformed classical PLS for most of the targets (quality criteria). Furthermore, it is important to update the models on the fly with incremental updating of the PLS space and/or with down-weighting older samples, as this significantly decreased the accumulated error trends of the prediction models compared to conventional updating. Reliable predictions of flatness quality (with around 10% error) and of RMSE values and transmissions (with around 15% errors) can be achieved with prediction horizons of up to 4 to 5 h into the future.
Choosing the best method for feature selection depends on the extent of a priori knowledge of the problem. The authors present two basic approaches. One involves computationally effective floating-search methods; the other trades off the requirement for a priori information for the distributions involved.
Plenty of feature selection methods are available in literature due to the availability of data with hundreds of variables leading to data with very high dimension. Feature selection methods provides us a way of reducing computation time, improving prediction performance, and a better understanding of the data in machine learning or pattern recognition applications. In this paper we provide an overview of some of the methods present in literature. The objective is to provide a generic introduction to variable elimination which can be applied to a wide array of machine learning problems. We focus on Filter, Wrapper and Embedded methods. We also apply some of the feature selection techniques on standard datasets to demonstrate the applicability of feature selection techniques.
Batch processes are characterized by inherent nonlinearity, multiplicity of operating phases, between-phase transient dynamics and batch-to-batch uncertainty that pose significant challenges for accurate state estimation and quality prediction. Conventional multi-model strategies, however, may be ill-suited for multiphase batch processes because the localized models do not specially take into account the complex transient dynamics between two consecutive operating phases. In this study, a novel Bayesian model averaging based multi-kernel Gaussian process regression (BMA-MKGPR) approach is proposed for state estimation and quality prediction of nonlinear batch processes with multiple operating phases and between-phase transient dynamics. A kernel mixture model strategy is first used to identify the different operating phases of batch processes and then the multi-kernel GPR models are built for all the identified phases. Further, the between-phase transitional stage is determined by the posterior probabilities of measurement samples with respect to the two consecutive phases so that the Bayesian model averaging strategy can be designed to incorporate the two localized GPR models for handling the between-phase transient dynamics. For an arbitrary test sample within the transitional stage, its posterior probabilities with respect to the local models corresponding to the two consecutive phases are set as the adaptive weightings to integrate the corresponding local GPR models for state estimation and quality prediction. The proposed BMA-MKGPR approach is applied to a multiphase batch polymerization process and the result comparison demonstrates that the presented method can effectively handle multiple nonlinear operating phases, between-phase transient dynamics and process uncertainty with fairly high prediction accuracies.
Recent years have seen an increase in the number of regression problems for which the predictor and/or response arrays have orders higher than two, i.e. multiway data. Examples are found in, e.g. industrial batch process analysis, chemical calibration using second-order instrumentation and quantitative structure–activity relationships (QSAR). As these types of problems increase in complexity in terms of both the dimensions and the underlying structures of the data sets, the number of options with respect to different types of scaling and regression models also increases. In this article, three methods for multiway regression are compared: unfold partial least squares (PLS), multilinear PLS and multiway covariates regression (MCovR). All three methods differ either in the structural model imposed on the data or the way the model components are calculated. Three methods of scaling multiway arrays are also compared, along with the option of applying no scaling. Three data sets drawn from industrial processes are used in the comparison. The general conclusion is that the type of data and scaling used is more important than the type of regression model used in terms of predictive ability. The models do differ, however, in terms of interpretability.
Many quality improvement (QI) programs including six sigma, design for six sigma, and kaizen require collection and analysis of data to solve quality problems. Due to advances in data collection systems and analysis tools, data mining (DM) has widely been applied for QI in manufacturing. Although a few review papers have recently been published to discuss DM applications in manufacturing, these only cover a small portion of the applications for specific QI problems (quality tasks). In this study, an extensive review covering the literature from 1997 to 2007 and several analyses on selected quality tasks are provided on DM applications in the manufacturing industry. The quality tasks considered are; product/process quality description, predicting quality, classification of quality, and parameter optimisation. The review provides a comprehensive analysis of the literature from various points of view: data handling practices, DM applications for each quality task and for each manufacturing industry, patterns in the use of DM methods, application results, and software used in the applications are analysed. Several summary tables and figures are also provided along with the discussion of the analyses and results. Finally, conclusions and future research directions are presented.
Supervision of batch bioprocess operations in real-time during the progress of a batch run offers many advantages over end-of-batch quality control. Multivariate statistical techniques such as multiway partial least squares (MPLS) provide an efficient modeling and supervision framework. A new type of MPLS modeling technique that is especially suitable for online real-time process monitoring and the multivariate monitoring charts are presented. This online process monitoring technique is also extended to include predictions of end-of-batch quality measurements during the progress of a batch run. Process monitoring, quality estimation and fault diagnosis activities are automated and supervised by embedding them into a real-time knowledge-based system (RTKBS). Interpretation of multivariate charts is also automated through a generic rule-base for efficient alarm handling. The integrated RTKBS and the implementation of MPLS-based process monitoring and quality control are illustrated using a fed-batch penicillin production benchmark process simulator.
Choosing the best method for feature selection depends on the
extent of a-priori knowledge of the problem. We present two basic
approaches. One involves computationally effective floating-search
methods; the other trades off the requirement for a-priori information
for the requirement of sufficient data to represent the distributions
involved. We've developed methods for statistical pattern recognition
that, based on the user's level of knowledge of a problem, can reduce
the problem's dimensionality. We believe that these methods can enrich
the methodology of subset selection for other fields of AI. This article
provides an overview of our methods and techniques. focusing on the
basic principles and their potential use
Chemicals manufacture by batch processes
Mixing machinery for rubber
- melotto
Methods and applications’
- J Wang
- Y Ma
- L Zhang
- R X Gao
- D Wu
R Interface to Keras.
- F Chollet
- J Allaire
Data-driven CFD simulation of an industrial semi-batch mixing process
- C Alfaro
- I Viejo
- S Izquierdo
Handbook of Industrial Mixing: Science and Practice.
- E L Paul
- V A Atiemo-Obeng
- S M Kresta
The specialty chemicals market to reach $1,273 bn by 2024
Data-driven CFD simulation of an industrial semi-batch mixing process
- alfaro