Search

To deal with the highly nonlinear and time-varying characteristics of Batch Process, a model named adaptive stacking approximate kernel based broad learning system is proposed in this paper. This model innovatively introduces the approximate kernel based broad learning system (AKBLS) algorithm and the Adaptive Stacking framework, giving it strong nonlinear fitting ability, excellent generalization ability, and adaptive ability. The Broad Learning System (BLS) is known for its shorter training time for effective nonlinear processing, but the uncertainty brought by its double random mapping results in poor resistance to noisy data and unpredictable impact on performance. To address this issue, this paper proposes an AKBLS algorithm that reduces uncertainty, eliminates redundant features, and improves prediction accuracy by projecting feature nodes into the kernel space. It also significantly reduces the computation time of the kernel matrix by searching for approximate kernels to enhance its ability in industrial online applications. Extensive comparative experiments on various public datasets of different sizes validate this. The Adaptive Stacking framework utilizes the Stacking ensemble learning method, which integrates predictions from multiple AKBLS models using a meta-learner to improve generalization. Additionally, by employing the moving window method—where a fixed-length window slides through the database over time—the model gains adaptive ability, allowing it to better respond to gradual changes in industrial Batch Process. Experiments on a substantial dataset of penicillin simulations demonstrate that the proposed model significantly improves predictive accuracy compared to other common algorithms. [ABSTRACT FROM AUTHOR]

The flexible job-shop scheduling problem (FJSP) with parallel batch processing machine (PBM) is one of those long-standing issues that needs cutting-edge approaches. It is a recent extension of standard flexible job shop scheduling problems. Despite their wide application and prevalence in practical production, it seems that current research on these types of combinatorial optimization problems remains limited and uninvestigated. More specifically, existing research mainly concentrates on the flow shop scenarios in parallel batch machines for job shop scheduling but few literature emphasis on the flexible job shop integration in these contexts. To directly address the above mentioned problems, this paper establishes an optimization model considering parallel batch processing machines, aiming to minimize the maximum completion time in operating and production environments. The proposed solution merges variable neighborhood search with multi-population genetic algorithms, conducting a neighborhood search on the elite population to reduce the likelihood of falling into local optima. Subsequently, its applicability was evaluated in computational experiments using real production scenarios from a partnering enterprise and extended datasets. The findings from the analyses indicate that the enhanced algorithm can decrease the objective value by as much as 15% compared to other standard algorithms. Importantly, the proposed approach effectively resolves flexible job shop scheduling problems involving parallel batch processing machines. The contribution of the research is providing substantial theoretical support for enterprise production scheduling. [ABSTRACT FROM AUTHOR]

In the realm of distributed computing frameworks, such as Apache Spark and MapReduce Hadoop, the efficacy of these frameworks varies across diverse applications and algorithms contingent upon distinctive evaluation metrics and critical parameters. This research paper diligently scrutinizes the extant body of research that compares these two frameworks concerning said evaluation metrics and parameters. Subsequently, it conducts empirical investigations to authenticate the performance of these frameworks in the context of an iterative Gradient Boosting Tree Regression (GBTR) algorithm. Remarkably, the comparative analyses in previous studies encompass a spectrum of iterative machine learning regression and classification techniques, batch processing, SQL, and Graph processing algorithms. Furthermore, numerous investigations have explored the application of machine learning algorithms encompassing logistic regression, Page Rank, K-Means, KNN, and the HiBench suite. This paper presents the comparison between the two distributed computing platforms on iterative GBTR for classification task on the HIGGS dataset from the physics domain and for the regression task on the Covid-19 dataset from the healthcare domain. The empirical findings corroborate that Apache Spark exhibits superior execution speed in iterative tasks when the available physical memory significantly exceeds the dataset size. Conversely, Hadoop outperforms Spark when dealing with substantial datasets or constrained physical memory resources. [ABSTRACT FROM AUTHOR]

This paper studies the use of varying threshold in the statistical process control (SPC) of batch processes. The motivation is driven by how when multiple phases are implicated in each repetition, the distributions of the features behind vary with phases or even the time; thus, it is inconsistent to uniformly bound them by an invariant threshold. In this paper, we paved a new path for learning and monitoring batch processes based on an efficient framework integrating a model termed conditional dynamic variational auto-encoder (CDVAE). Phase indicators are first used to split the data and are then separated, serving as an extra input for the model in order to alleviate the learning complexity. Dissimilar to the routine using features across all timescales, only features relevant to local timestamps are aggregated for threshold calculation, producing a varying threshold that is more specific for the process variations occurring among the timeline. Leveraged upon this idea, a fault detection panel is devised, and a deep reconstruction-based contribution diagram is illustrated for locating the faulty variables. Finally, the comparative results from two case studies highlight the superiority in both detection accuracy and diagnostic performance. [ABSTRACT FROM AUTHOR]

This paper describes a correlation-based batch process for addressing high dimensional imputation problems. There are relatively few algorithms designed to efficiently handle imputation of missing data in high dimensional contexts. Fewer still are flexible enough to natively handle mixed-type data, often requiring lengthy pre-processing to get the data into proper shape, and then post-processing to return the data to usable form. Such decisions as well as assumptions made by many methods (e.g., data generating process) limit their performance, flexibility, and usability. Built on a set of complementary algorithms for nonparametric imputation via chained random forests, I introduce a batching process to ease computational costs associated with high dimensional imputation by subsetting data based on ranked cross-feature absolute correlations. The algorithm then imputes each batch separately, and joins imputed subsets in the final step. The process, hdImpute, is fast and accurate. As a result, high dimensional imputation is more accessible, and researchers are not forced to decide between speed or accuracy. Complementary software is available in the form of an R package, and is openly developed on Github under the MIT public license. In the spirit of open science, collaboration and engagement with the actively developing software are encouraged. [ABSTRACT FROM AUTHOR]

Following the pioneering challenge for joint optimization of decisions in supply chains, this paper newly provides an integrated framework to efficiently fulfill a productionplanning and distribution problem in effect. In such an integrated scheme, a set of perishable family products is manufactured on a single batch-processing machine. These products are dispatched to the customers by a third-party logistics service provider with only two types of licensed eco-friendly transportation facilities. In order to efficiently deliver the manufactured products before they become unusable, we propose a combined shipment structure. To accomplish this, the problem is formulated in the context of a mixedinteger linear programming model. In particular, we aim to establish two manufacturing policies based on both increasing and decreasing rates of production and also two delivery policies expressing distinct preferences in fulfilling the customers' demands. The cost structures obtained from the established integrated planning and the resulting distribution configurations are investigated as well. Further, four heuristic algorithms are developed for solving the problem for each hybrid production/distribution scheme derived from the former policies. A numerical study is conducted to compare the mentioned procedures, illustrating the preferable efficiency of the plan obtained through the hybridization of the increasing-production-rate and decreasing-delivery-distance policies. [ABSTRACT FROM AUTHOR]

Currently, petrochemical plastics dominate the food service industry due to their good mechanical properties and barrier against heat, water vapor, carbon dioxide, and oxygen. This widespread use is not only harmful to humans but also to the ecosystem as synthetic plastics disrupt ecological balance and deplete petroleum-based oil resources. Researchers and manufacturers are continuously addressing this problem by developing bio-based alternatives that provide numerous advantages including structural flexibility, biodegradability, and effective barrier properties. However, the high cost of production and unavailability of equipment for batch processing impede the potential for widespread manufacturing. Natural fibers mixed with bio-based adhesives derived from plants provide one of the biggest potential sources of bio-based materials for the food container industry. Not only does this address the issue of high raw material cost but it also has the potential to become sustainable once processing steps have been optimized. In this review, the current findings of several research related to the production of bio-based disposable food containers, packaging, and composites made from bio-based materials and bio-based adhesives are critically discussed. Several properties and characteristics important to the production of food service containers and primary packaging, as well as the existing challenges and future perspectives, are also highlighted. [ABSTRACT FROM AUTHOR]

Colour pattern variation provides biological information in fields ranging from disease ecology to speciation dynamics. Comparing colour pattern geometries across images requires colour segmentation, where pixels in an image are assigned to one of a set of colour classes shared by all images. Manual methods for colour segmentation are slow and subjective, while automated methods can struggle with high technical variation in aggregate image sets. We present recolorize, an R package toolbox for human‐subjective colour segmentation with functions for batch‐processing low‐variation image sets and additional tools for handling images from diverse (high‐variation) sources. The package also includes export options for a variety of formats and colour analysis packages. This paper illustrates recolorize for three example datasets, including high variation, batch processing and combining with reflectance spectra, and demonstrates the downstream use of methods that rely on this output. [ABSTRACT FROM AUTHOR]

A scheduling problem for parallel batch processing machines (BPMs) with jobs having unequal ready times in semiconductor wafer fabrication facilities (wafer fabs) is studied in this paper. A blended objective function combining the total weighted tardiness (TWT) and the total electricity cost (TEC) under a time-of-use (TOU) tariff is considered. A genetic programming (GP) procedure is designed to automatically discover priority indices for a heuristic scheduling framework. Results of computational experiments are reported that demonstrate that the learned priority indices lead to high-quality schedules in a short amount of computing time. [ABSTRACT FROM AUTHOR]

In the mechanical cutting industry, trial production is used for predicting and evaluating the quality of product processes before batch production, and it can be expressed through the qualification rate. However, it cannot objectively and comprehensively evaluate the quality of product processes. This study optimizes the analysis of outliers and stability in mathematical statistics to better apply it in the mechanical cutting industry; then, it combines them with process capability analysis. Simultaneously, considering the non-normal distribution of process parameters, a batch production-prediction model is proposed. The reliability of batch production-prediction model is verified by the diameter, roundness and roughness of structural common samples. Meanwhile, for other mechanical parts in the mechanical cutting industry, the model proposed in this paper can be used to quickly and accurately predict and evaluate batch production. [ABSTRACT FROM AUTHOR]

The continuous annealing process (CAP) is a crucial process of steel production, which has a significant impact on the uniformity and stability of mechanical properties. A novel batch monitoring process based on kernel dissimilarity (KDISSIM) and Kmeans++ is proposed in this paper, focusing on problems such as unequal sample lengths between batches and nonlinearity between variables. First, KDISSIM is used to describe the dissimilarity between batches. Secondly, Kmeans++ is employed to improve the accuracy of clustering tasks based on historical batches. The largest cluster is considered to be at a relatively stable control level, and these batches are further used as training data. Then, the center batch and boundary batch of the training set are used as the reference batch and monitoring threshold for the monitoring model, respectively. Finally, the effectiveness of the proposed method is verified via the actual CAP data, providing a feasible solution for CAP batch monitoring. [ABSTRACT FROM AUTHOR]

In the passive bistatic radar (PBR) system, methods exist to address the issue of detecting weak targets without being influenced by non-ideal factors from adjacent strong targets. These methods utilize the sparsity in the delay-Doppler domain of the cross ambiguity function (CAF) to detect weak targets. However, the modeling and solving of this method involve substantial memory consumption and computational complexity. To address these challenges, this paper establishes a target detection model for PBR based on batch processing of sparse representation and recovery. This model partitions the CAF into blocks, identifies blocks requiring processing based on the presence of targets, and improves the construction and utilization of the measurement matrix. This results in a reduction in the computational complexity and memory resource requirements for sparse representation and recovery, and provides favorable conditions for parallel execution of the algorithm. Experimental results indicate that the proposed approach increases the number of blocks by a factor of four, and reduces the number of real multiplications by approximately an order of magnitude. Hence, compared with the traditional approach, the proposed approach enables fast and stable detection of weak targets. [ABSTRACT FROM AUTHOR]

Lithium (Li) is vital to the world economy as an irreplaceable element in new-generation sustainable energy applications. Quantifying Li levels in clay minerals, a key new resource, supports extensive mineralization surveys. The major limitation in these analyses is complete decomposition, which often requires the use of strong acids and is labor-intensive, particularly in batch processing. This paper presents a partial extraction strategy for quantifying Li and multiple elements, employing ammonium hydrogen fluoride to extract from clay minerals while avoiding the use of various strong acids. Following extraction, the efficiency for Li reaches 98.61%, with values ranging from 62.68% to 91.43% for multiple elements including three major elements (Ca, Fe, Mg) and eleven trace elements (Be, Co, Cr, Cu, Ga, Mn, Ni, P, Rb, Sr, V), demonstrating favorable precision (RSD below 7.34%). This approach offers a promising tool for a simple and efficient batch analysis in the survey of mineralization in Li-bearing clay deposits. [ABSTRACT FROM AUTHOR]

The structural components of large-scale public construction projects are more complex than those of ordinary residential buildings, with irregular and diverse components, as well as a large number of repetitive structural elements, which increase the difficulty of BIM-modeling operations. Additionally, there is a significant amount of inherent parameter information in the construction process, which puts forward higher requirements for the application and management capabilities of BIM technology. However, the current BIM software still has deficiencies in the parameterization of complex and irregular structural components, fine modeling, and project management information. To address these issues, this paper takes Grasshopper as the core parametric tool and Revit as the carrier of component attribute information. It investigates the parametric modeling logic of Grasshopper and combines the concepts of parameterization, modularization, standardization, and engineering practicality to create a series of parametric programs for complex structural components in building projects. This approach mainly addresses intricate challenges pertaining to the parametric structural shapes (including batch processing) and parametric structural attributes (including the batch processing of diverse attribute parameters), thereby ensuring the efficiency in BIM modeling throughout the design and construction phases of complex building projects. [ABSTRACT FROM AUTHOR]

Introduction: In recent decades, numerous large survey projects have been initiated to enhance our understanding of the cosmos. Among these, the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) stands out as a flagship project of the Stage IV cosmology imaging surveys, offering an open-source framework for data management and processing adaptable to various instruments. Methods: In this paper, we introduce the 'obs_mccd' software package, designed to serve as a bridge linking raw data from generic mosaic-CCD instruments to the LSST data management framework. The package also facilitates the deployment of tailored configurations to the pipeline middleware. To validate our data processing pipeline, we processed a batch of realistic data from a commissioning wide-field telescope. Results: We established a prototype of the quality control (QC) system capable of assessing image quality parameters such as PSF size, ellipticity, and astrometric calibration. Our findings indicate that using a fifth-order polynomial for astrometric calibration effectively characterizes geometric distortion, achieving a median average geometric distortion residual of 0.011 pixel. Discussion: When comparing the performance of our pipeline to our inhouse pipeline applied to the same dataset, we observed that our new 'obs_mccd' pipeline offers improved precision, reducing the median average geometric distortion residual from 0.016 pixel to 0.011 pixel. This enhancement in performance underscores the benefits of the obs_mccd package in managing and processing data from wide-field surveys, and it opens up new avenues for scientific exploration with smaller, flexible survey systems complementing the LSST. [ABSTRACT FROM AUTHOR]

Quality‐related fault detection has become a hot research topic in recent years. It is not reliable to measure quality‐related relationships only by mutual information among process variables and single‐quality variables. Frequent alarms for quality‐unrelated faults seriously affect the normal operation of industrial production. At the same time, the strong nonlinearity of the process data leads to the difficulty of feature extraction. In this paper, we propose a fault detection algorithm based on nonlinear quality‐related neighborhood embedding neural orthogonal mapping (QR‐NENOM). First, quality‐related and quality‐unrelated variables are selected by Bayesian fusion mutual information, and the weighted method of mutual information is used to enhance the quality‐related information and suppress the quality‐unrelated information. Second, local manifold information is obtained by reconstructing nearest neighbors of process data, and key features are extracted by the nonlinear method composed of neural network and orthogonal mapping. Then, statistical indicators are established to complete fault detection. Finally, the nonlinear feature extraction ability of NENOM is verified by numerical examples, and the QR‐NENOM algorithm proposed in this paper is applied to the penicillin fermentation process. Comparative experiments show that QR‐NENOM has better detection performance for quality‐related faults and fewer alarms for quality‐unrelated faults. [ABSTRACT FROM AUTHOR]

The study of living microorganisms using resource allocation models has been key in elucidating natural behaviors of bacteria, by allowing allocation of microbial resources to be represented through optimal control strategies. The approach can also be applied to research in microbial cell factories, to investigate the optimal production of value-added compounds regulated by an external control. The latter is the subject of this paper, in which we study batch bioprocessing from a resource allocation perspective. Based on previous works, we propose a simple bacterial growth model accounting for the dynamics of the bioreactor and intracellular composition, and we analyze its asymptotic behavior and stability. Using optimization and optimal control theory, we study the production of biomass and metabolites of interest for infinite- and finite-time horizons. The resulting optimal control problems are studied using Pontryagin's maximum principle and numerical methods, and the solutions found are characterized by the presence of the Fuller phenomenon (producing an infinite set of switching points occurring in a finite-time window) at the junctions with a second-order singular arc. The approach, inspired by biotechnological engineering, aims to shed light upon the role of cellular composition and resource allocation during batch processing and, at the same time, poses very interesting and challenging mathematical problems. [ABSTRACT FROM AUTHOR]

For decades, soft sensors have been extensively renowned for their efficiency in real-time tracking of expensive variables for advanced process control. However, despite the diverse efforts lavished on enhancing their models, the issue of label sparsity when modeling the soft sensors has always posed challenges across various processes. In this paper, a fledgling technique, called co-training, is studied for leveraging only a small ratio of labeled data, to hone and formulate a more advantageous framework in soft sensor modeling. Dissimilar to the conventional routine where only two players are employed, we investigate the efficient number of players in batch processes, making a multiple-player learning scheme to assuage the sparsity issue. Meanwhile, a sliding window spanning across both time and batch direction is used to aggregate the samples for prediction, and account for the unique 2D correlations among the general batch process data. Altogether, the forged framework can outperform the other prevalent methods, especially when the ratio of unlabeled data is climbing up, and two case studies are showcased to demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

This paper studies the customer order scheduling problem in the context of additive manufacturing. The study discusses an integrated problem involving the nesting of parts as well as the scheduling of batches of nested parts onto unrelated parallel machines. A mixed-integer programming model is presented, based on existing formulations from the literature, that integrates different materials and sequence-dependent setup times. Additionally, a metaheuristic based on an iterated local search is proposed for the problem configuration under consideration. Focusing on minimizing the total weighted tardiness of orders, the efficiency of the heuristic approach is evaluated using comprehensive test data. Further, we show the importance of the considered order-related objective by using qualitative analysis. [ABSTRACT FROM AUTHOR]

Traditional two-dimensional dynamic fault detection methods describe nonlinear dynamics by constructing a two-dimensional sliding window in the batch and time directions. However, determining the shape of a two-dimensional sliding window for different phases can be challenging. Samples in the two-dimensional sliding windows are assigned equal importance before being utilized for feature engineering and statistical control. This will inevitably lead to redundancy in the input, complicating fault detection. This paper proposes a novel method named attention-based two-dimensional dynamic-scale graph autoencoder (2D-ADSGAE). Firstly, a new approach is introduced to construct a graph based on a predefined sliding window, taking into account the differences in importance and redundancy. Secondly, to address the training difficulties and adapt to the inherent heterogeneity typically present in the dynamics of a batch across both its time and batch directions, we devise a method to determine the shape of the sliding window using the Pearson correlation coefficient and a high-density gridding policy. The method is advantageous in determining the shape of the sliding windows at different phases, extracting nonlinear dynamics from batch process data, and reducing redundant information in the sliding windows. Two case studies demonstrate the superiority of 2D-ADSGAE. [ABSTRACT FROM AUTHOR]

The extensive consumption of energy in manufacturing has led to a large amount of greenhouse gas emissions that have caused an enormous effect on the environment. Therefore, investigating how to reduce energy consumption in manufacturing is of great significance to cleaner production. This paper considers an energy-conscious unrelated parallel batch processing machine scheduling problem under time-of-use (TOU) electricity prices. Under TOU, electricity prices vary for different periods of a day. This problem is grouping jobs into batches, assigning the batches to machines and allocating time to the batches so as to minimize the total electricity cost. A mixed-integer linear programming model and two groups of heuristics are proposed to solve this problem. The first group of heuristics first forms batches, assigns the batches to machines and finally allocates time to the batches, while the second group of heuristics first assigns jobs to machines, batches the jobs on each machine and finally allocates time to each batch. The computational results show that the SPT-FBLPT-P1 heuristic in the second group can provide high-quality solutions for large-scaled instances in a short time, in which the jobs are assigned to the machines based on the shortest processing time rule, the jobs on each machine are batched following the full-batch longest processing time algorithm, and the time is allocated to each batch following an integer programming approach. The MDEC-FBLPT-P1 heuristic that uses the minimum difference of the power consumption algorithm to assign the jobs also performed well. [ABSTRACT FROM AUTHOR]

Mixnets are an instrument to achieve anonymity. They are generally a sequence of servers that apply a cryptographic process and a permutation to a batch of user messages. Most use asymmetric cryptography, with the high computational cost that this entails. The main objective of this study is to reduce delay in mixnet nodes. In this sense, this paper presents a new scheme that is based only on symmetric cryptography. The novelty of this scheme is the use of binary graphs built by mixnet nodes. The root node collects user keys and labels without knowing their owners. After feeding each node by its graph, they can establish a random permutation and relate their keys to the incoming batch positions through labels. The differences with previous symmetric schemes are that users do not need long headers and nodes avoid the searching process. The outcomes are security and efficiency improvements. As far as we know, it is the fastest mixnet system. Therefore, it is appropriate for high-throughput applications like national polls (many users) or debates (many messages). [ABSTRACT FROM AUTHOR]

This paper presents a new optimisation method for PID controller cascaded with a lead-lag compensator (PIDC). Parameters of the controller are obtained by solving the constrained optimisation problem. We propose two variants of the optimality criterion. The first one is defined through the max–min optimisation problem wherein objective function is the amplitude frequency response of the PIDC controller. The second one is based on an effective approximation of the minimum value of the amplitude frequency response of the PIDC controller. Consequently, we obtain a computationally less expensive problem. Both variants of optimality criterion result in efficient load disturbance and noise rejection, while robustness is ensured by constraining the value of the maximum sensitivity Ms. Good reference shaping is supported with proper constraints based on the Amplitude Optimum (AO) principle. Numerous batches of processes typically encountered in the industry are used to demonstrate the effectiveness of the proposed design method. [ABSTRACT FROM AUTHOR]

Distributed Scatterers Interferometry (DS-InSAR) has been widely applied to increase the number of measurement points (MP) in complex mountainous areas with dense vegetation and complicated topography. However, DS-InSAR method adopts batch processing mode. When new observation data acquired, the entire archived data is reprocessed, completely ignoring the existing results, and not suitable for high-performance processing of operational observation data. The current research focuses on the automation of SAR data acquisition and processing optimization, but the core time series analysis method remains unchanged. In this paper, based on the traditional Sequential Estimator proposed by Ansari in 2017, a Recursive Sequential Estimator with Flexible Batches (RSEFB) is improved to divide the large dataset flexibly without requirements on the number of images in each subset. This method updates and processes the newly acquired SAR data in near real-time, and obtains long-time sequence results without reprocessing the entire data archived, helpful to the early warning of landslide disaster in the future. 132 Sentinel-1 SAR images and 44 TerraSAR-X SAR images were utilized to inverse the line of sight (LOS) surface deformation of Xishancun landslide and Huangnibazi landslide in Li County, Sichuan Province, China. RSEFB method is applied to retrieve time-series displacements from Sentinel-1 and TerraSAR-X datasets, respectively. The comparison with the traditional Sequential Estimator and validation through Global Position System (GPS) monitoring data proved the effectiveness and reliability of the RSEFB method. The research shows that Xishancun landslide is in a state of slow and uneven deformation, and the non-sliding part of Huangnibazi landslide has obvious deformation signal, so continuous monitoring is needed to prevent and mitigate possible catastrophic slope failure events. [ABSTRACT FROM AUTHOR]

Data-driven based batch process monitoring is of critical importance in ensuring stable operating processes and consistent product quality. For long-duration batch processes, it is unrealistic to involve expensive data to train a statistical model for monitoring. To model the inherently batch-wise and variable-wise dynamics, nonlinearity, and time-varying characteristics, this paper proposes a local learning-based two-dimensional subspace identification (LL-2D-SID) scheme based on the similarity between the ongoing batch and the previous batches. The similarity is estimated by the extended extrapolative time-warping. Unlike the conventional statistical models using rich batch data, LL-2D-SID through online optimizing mechanism using limited batch data still has good prediction performance. The application of the sintering process in the polytetrafluoroethylene production has demonstrated that the LL-2D-SID based process monitoring scheme can not only accurately track temperature changes but also timely give fault alarms with a lower error alarm rate than the other SID-based process monitoring schemes. • Local learning-based 2-dimensional subspace identification (LL-2D-SID) is proposed. • Limited batch data of batch processes can be used to train LL-2D-SID. • Extended XTW is introduced to estimate similarity of data between current and previous batches. • Modeling data changes are integrated into SID by updating projection matrix. • Efficient implementation ensures LL-2D-SID to online monitor PTFE process. [ABSTRACT FROM AUTHOR]

To solve some scheduling problems of batch processes based on timed Petri net models, timed extended reachability graphs (TERGs) and approximated TERGs can be used. Such graphs abstract temporal specifications and represent parts of timed languages. By exploring the feasible trajectories in a TERG, optimal schedules can be obtained with respect to the makespans of batch processes that are modeled by timed Petri nets. Nevertheless, the rapid growth of the number of states in a TERG makes the problem intractable for large systems. In this paper, we improve the existing clustering TERG approach, and we make it suitable for large sized batch processes. We also enlarge a systematic approach to model batch processes with timed Petri nets. Finally, a comprehensive example of scheduling problem is studied for an archetypal chemical production plant in order to illustrate the efficiency of the proposed approach. • The scheduling issue of batch chemical processes is formalized with timed Petri nets. • A graph named ClusTERG approximates the state space through hierarchical clustering. • The approximation error of this ClusTERG is far less than other approximations. • Such an approach is used to obtain near-optimal schedules of a batch process. [ABSTRACT FROM AUTHOR]

In this paper, an integrated tube robust iterative learning model predictive control (Tube‐RILMPC) strategy based on the dynamic partial least squares (DyPLS) identified algorithm is proposed. The problems of large amount of online data calculation and input and output variable dimensions disaster in the original variable space are solved. This integrated Tube‐RILMPC strategy enhances the tracking performance and robustness of two‐dimensional (2D) control system. The output trajectories of system are located in the tube the nominal trajectory, which reduces the modelling error caused by the uncertain model. Based on the worst‐case performance index of ellipsoidal uncertainty and polytopic uncertainty, a robust iterative learning control (ILC) strategy is designed. Finally, the superiority of the proposed control algorithm is verified by comparative simulation. [ABSTRACT FROM AUTHOR]

In order to solve the problem of converting a large amount of original GNSS receiver observation data into RINEX format files independent of the receiver during satellite positioning measurement in railway line engineering plane control networks, this paper used the C # language for secondary development of the program. The GNSS receiver observation data of Trimble Company was taken as the research object, and the syntax rules of the batch processing file of the GNSS receiver original observation data which provided by the company decoding program Convert To RINEX were analyzed. Then, the batch processing file calling method of the program was used to develop the Trimble GNSS observation data batch processor. After engineering verification, this batch of processor software could conveniently and quickly convert the massive raw data of Trimble GNSS receivers into RINEX format files independent of the receivers, and can be applied to various large-scale satellite measurement projects such as railway line engineering plane control network satellite positioning measurement. [ABSTRACT FROM AUTHOR]

Fault diagnosis plays a pivotal role in identifying the root causes of a fault. Current fault diagnosis methods encounter the shortcomings being unable to assess the fault amplitude or having low efficiency for batch fermentation process. In order to solve the above problems, this paper proposes a fault detection model named convolutional neural network based on variational autoencoder (CNN-VAE) and a fault diagnosis based on counterfactual inference (FDCI). To begin with, quality-related process variables are selected using mutual information (MI). Next, a two-dimensional moving window is used to obtain input sequences from the process data. Then, two statistics from the latent and residual domains of the CNN-VAE model are constructed for fault detection. Additionally, once a fault occurs, FDCI is used to locate the root cause of a fault. Finally, a simulation process and a real-world L. plantarum batch fermentation process are provided to demonstrate the effectiveness of the proposed approache. • A novel model named CNN-VAE is proposed for batch fermentation processes monitoring. • An innovative fault diagnosis strategy named FDCI is proposed. • A simulation and an experiment verify the efficiency of the CNN-VAE and FDCI strategy. [ABSTRACT FROM AUTHOR]

This paper studies the challenges involved in production planning in coproduction systems, specifically the production of semiconductor chips for light-emitting diodes (LEDs). The production output in this industry is characterized by a stochastic distribution over the targeted production metric; thus the whole range of production is not suitable for a specific application. We formulate a novel stochastic profit optimization problem with random production output and random demand—based on information gleaned from interactions with a large integrated LED manufacturer—and determine the optimal production parameter setting and the batch size analytically; we solve the problem exactly in the special case of a single customer specification, and approximately in the case of an arbitrary number of customer specifications. We find that the optimal production setting depends on the sharpness of the density function governing the production output distribution and the range of parameter settings that are acceptable to customers. We show analytically that even under perfectly symmetric conditions, the optimal production setting is not necessarily symmetrically located with respect to the output range. We complement our analytical results with a Monte Carlo simulation of an augmented model with service level constraints. Our simulation results show that the approximate model that we develop serves as an excellent proxy for the intractable exact model, and illustrates the interplay between production output randomness, demand randomness, service levels, and production yield. [ABSTRACT FROM AUTHOR]

Data‐driven soft sensor models have been extensively utilized in industrial processes. Batch processes are usually employed to manufacture low‐volume and high value‐added products in chemical, materials, and pharmaceutical industries. The most distinctive features of batch process lie in nonlinear, repetition, and slow time varying characteristics. In this paper, a data‐driven soft sensor modelling method based on linear slow feature analysis (LSFA) and least squares support vector regression (LSSVR) is proposed. In this method, LSFA was used to effectively capture the driving force behind the data features that change as slowly as possible. Then, a LSSVR model was constructed between the extracted slow feature variables and quality variables. Finally, a numerical example, industrial penicillin fermentation processes, and cobalt oxalate synthesis process were utilized to confirm the prediction accuracy and model reliability of the proposed approach. [ABSTRACT FROM AUTHOR]

Asymmetric organocatalysis has been recognized as one of the "top 10 emerging technologies" in chemistry by IUPAC in 2019. Its potential to make chemical processes more sustainable is promising, but there are still challenges that need to be addressed. Developing new and reliable enantioselective processes for reproducing batch reactions on a large scale requires a combination of chemical and technical solutions. In this manuscript, we combine a robust immobilized chiral phosphoric acid with a new packed-bed reactor design. This combination allows scaling up of the enantioselective addition of thiols to imines from a few milligrams to a multi-decagram scale in a continuous flow process without physical or chemical degradation of the catalyst. [ABSTRACT FROM AUTHOR]

The design of batch food processing plants is complex which requires the use of advanced simulation and optimisation methods. This paper presents how existing methods for multi-scale design and multi-objective optimisation can be combined together while carrying out the integrative design of these complex systems. To implement the Methodology for the Integrated, Multi-scale and Multi-Objective Design of Systems (MIMMODS), 8 tasks must be completed. The goal of the first 6 tasks is to build a design support tool that (i) simulates the behaviour of the processing plant and estimates its performance at different functional levels and whatever design variables it is made up of, (ii) takes into account the preferences of the decision-maker to convert the performances of a design solution into desirability indices and (iii) searches for the design solution(s) that best satisfies the design objectives and the preferences of the decision-maker. When the design support tool is functioning, the results have to be visualised and analysed in order to validate whether the resulting design solution is satisfactory, realistic, feasible and consistent or whether a new iteration of the methodology needs to be conducted to refine the design support tool. [ABSTRACT FROM AUTHOR]

This paper proposes an extended state observer (ESO) based data-driven set-point learning control (DDSPLC) scheme for a class of nonlinear batch processes with a priori P-type feedback control structure subject to nonrepetitive uncertainties, by only using the process input and output data available in practice. Firstly, the unknown process dynamics is equivalently transformed into an iterative dynamic linearization data model (IDLDM) with a residual term. A radial basis function neural network is adopted to estimate the pseudo partial derivative information related to IDLDM, and meanwhile, a data-driven iterative ESO is constructed to estimate the unknown residual term along the batch direction. Then, an adaptive set-point learning control law is designed to merely regulate the set-point command of the closed-loop control structure for realizing batch optimization. Robust convergence of the output tracking error along the batch direction is rigorously analyzed by using the contraction mapping approach and mathematical induction. Finally, two illustrative examples from the literature are used to validate the effectiveness and advantage of the proposed design. • Novel extended state observer (ESO) based data-driven set-point learning control (DDSPLC). • Iterative dynamic linearized data model (IDLDM) for nonlinear batch processes. • Use the radial basis function neural network (RBFNN) to approximate pseudo partial derivative. • Set-point learning law with an adaptive learning gain for a priori P-type feedback structure. • Robust convergence of the resulting ILC system along the batch direction is rigorously analyzed. [ABSTRACT FROM AUTHOR]

This paper studies the multi-objective problem of scheduling n two-component jobs on a fabrication machine with bounded batch capacity in terms of the number of jobs. Each job consists of two components, one is common among all jobs (called standard component) and the other is unique to itself (called specific component). The machine processes all components so that it might become a capacitated bottleneck machine. Standard components have equal processing times. They are fabricated in batches sequentially on the machine, and a setup time is required to fabricate a batch. Each batch contains the standard components of at most b(b < n) jobs. Specific components are manufactured individually, therefore their associated setup times could be absorbed into their processing times. Standard components in a batch are not available until all these components are completed (meaning that the processing time of a batch is equal to the total processing time of the standard components in it), whereas a specific component is available on completion of its processing. A job is completed when both its two components are completed and available. For simultaneous optimization of makespan and maximum lateness, an O(n3)-time algorithm is obtained. Through a careful use of the heap data structure, the time bound can be improved to O(n2 log n). For hierarchical optimization of two maximum lateness objectives and makespan, an O(n5)-time algorithm is obtained, which can be improved to run in time O(n4). [ABSTRACT FROM AUTHOR]

Several strategies to synthesize desired 1,2,4‐triazolo[1,5‐a]pyridine‐2‐carboxylate targets have been reported over the years. The most convenient way features the preparation of the precursor triazolopyridine‐N‐oxide through a condensation step between sulfilimines and a nitrile oxide species, followed by a deoxygenation step. This paper presents a detailed work on the synthesis of [1,2,4]triazolo[1,5‐a]pyridine‐2‐carboxylate‐N‐oxide, featuring a synergistic experimental‐theoretical approach. Herein, we report the development of an efficient and straightforward method to prepare ethyl [1,2,4]triazolo[1,5‐a]pyridine‐2‐carboxylate 3‐oxide in continuous flow. The transfer from batch to flow processing resulted in a significant boost in isolated yield (53 % vs. 31 %) and a decrease in the simultaneous presence of starting materials and product in the reaction media from 4 hours to 3.5 minutes. An in‐depth mechanistic study of the reaction using density functional theory provided a deeper understanding of the whole reaction manifold and key indications on how to further improve the process in flow. [ABSTRACT FROM AUTHOR]

Domain generalization person re-identification (re-ID) is a more realistic task that aims to learn a model with multiple labeled source domains and generalize its inference to an unseen domain. However, under joint training of multi-source domains, some difficulties such as domain imbalance, domain shifts and small training batches not only influence the representation learning of the model but also lead to poor generalization performance. In this work, we enhance the generalization performance by proposing two strategies including knowledge accumulation and distribution enhancement for multi-source domain generalization person re-ID. Specifically, we encourage the learning of semantically significant features globally by establishing a simple but effective knowledge accumulation feature classifier (KAFC). In which, continuous learning guided by the label information explicitly provides stable prototype matching for each source domain, directly solving the problem that unstable parameter updates due to the small-batch data and source domain shifts. Secondly, to enhance the generalization ability and learn more robust representations, a multi-mix batch normalization (MMBN) module is introduced to generate the mixture features with cross-domain distribution information, where an approach based on the exponential moving average is adopted for capturing the domain distribution knowledge. Extensive experiments on multiple widely-used benchmarks demonstrate that our method can effectively improve the generalization capability on unseen domains. [ABSTRACT FROM AUTHOR]

Anaerobic digestion (AD) is a process of biochemical decomposition by anaerobic bacteria. Organic solid waste, subjected to anaerobic digestion, produces organic fertilizer and biogas, composed of methane, carbon dioxide, and other gases. The AM2 model describes the AD system and is the most widely used model for dynamic behavior analysis and control of AD processes. One of the most critical variables for system analysis is the concentration of volatile fatty acids (VFA). The behavior of the concentration of VFA depends on the dilution rate. This, in turn, depends on the performance parameters of producing and consuming VFA (k2 and k3). This paper presents a deterministic method to calculate the k2 and k3 parameters, from the dilution rate dynamics and Olson method for indirect validation of the parameters based on the direct validation of the concentration of VFA. Model results for VFA concentration showed an error of <0.4%. An error of <1.98% was found between the theoretical model and the experimental data. Overall, a global error of <2.37% gives a reliability to the proposed method to determine k2 and k3. [ABSTRACT FROM AUTHOR]

Quality monitoring is an important tool for ensuring the safe operation of batch processes and the high quality of the final products. However, the inherent non‐linear, dynamic, and batch characteristics make the quality monitoring of batch process still have some difficulties. To solve these problems, this paper proposes a batch quality monitoring model based on a temporal convolutional network with a depthwise separable coordinated attention module. Firstly, a method of data unfolding incorporating sliding windows is proposed to unfold and stack the data along the direction of the variables, and a variable selection method of maximum information coefficient fused with Monte Carlo sampling is proposed to select the process variables related to the quality variables. Secondly, we take the traditional temporal convolutional network as the base network and decouple the correlation between the batch data by using depthwise separable convolution. At the same time, we utilize coordinate attention to extract data features in different spatial directions to ensure the effectiveness of quality monitoring. Finally, the feasibility and robustness of the proposed model are verified by a nonlinear numerical example and an industrial‐scale penicillin fermentation process. The experimental results show the proposed model has lower false alarm rate and false negative rate and can be used to maintain the product quality of the actual batch process. [ABSTRACT FROM AUTHOR]

In this paper, a new off-policy two-dimensional (2D) reinforcement learning approach is proposed to deal with the optimal tracking control (OTC) issue of batch processes with network-induced dropout and disturbances. A dropout 2D augmented Smith predictor is first devised to estimate the present extended state utilizing past data of time and batch orientations. The dropout 2D value function and Q-function are further defined, and their relation is analyzed to meet the optimal performance. On this basis, the dropout 2D Bellman equation is derived according to the principle of the Q-function. For the sake of addressing the dropout 2D OTC problem of batch processes, two algorithms, i.e., the off-line 2D policy iteration algorithm and the off-policy 2D Q-learning algorithm, are presented. The latter method is developed by applying only the input and the estimated state, not the underlying information of the system. Meanwhile, the analysis with regard to the unbiasedness of solutions and convergence is separately given. The effectiveness of the provided methodologies is eventually validated through the application of a simulated case during the filling process. • The 2D model-free control method can solve a dropout 2D OTC problem for the batch processes. • The 2D Q-learning method can find the optimal gain of the control law better. • The analysis of unbiasedness and convergence are given by the rigorous theoretical proof. • The proposed method for dropout OTC has the merit to exempt the effect of the probing noises and to produce unbiased solution. [ABSTRACT FROM AUTHOR]

This paper presents a mathematical programming-based solution approach for the scheduling problem of batch-processing parallel machines with eligibility constraints. A case study has been presented in the semiconductor industry, where the ovens are scheduled for the underfill cure operation of products. The case includes constraints, such as oven-product eligibility restrictions, loading constraints for the batching of products for ovens, daily production requirements, and oven capacity constraints. In this study, we also assess the difference between creating batches of a single product type or different product types to be allocated to the ovens. The case study results have shown that the proposed models, in comparison to the current situation, increase the occupancy rate of ovens. The execution of the models aids the company in gaining visibility on the scheduling of ovens and successfully managing the production plan and order commitment. The proposed models have been effective and supportive of the semiconductor company. [ABSTRACT FROM AUTHOR]

Although a proportional integral derivative type iterative learning control (PIDILC) scheme can achieve good performance, its application is limited by open‐loop structure, parameter tuning, and initial state. In this paper, a novel PIDILC optimized by two‐dimensional infinite horizon linear quadratic regulator (PIDILC‐2D‐IHLQR) is proposed. First, by synthesizing the advantage of the conventional PIDILC method and proportional integral derivative (PID) strategy, a novel closed‐loop PIDILC scheme is obtained. Then, a novel two‐dimensional infinite horizon linear quadratic regulator (2D‐IHLQR) is developed to optimize the parameters of the PIDILC strategy. The limitations of parameter tuning and initial state are solved by this PIDILC‐2D‐IHLQR method. Therefore, the proposed method not only solves the aforementioned limitations but also inherits the advantages of PIDILC algorithm, PID method, and the novel 2D‐IHLQR scheme. Moreover, a stability condition is given based on Lyapunov theory and it can help judge whether the selection of control parameters meets the stability condition. The effectiveness of the proposed method is demonstrated by the case study on an injection modelling process. [ABSTRACT FROM AUTHOR]

Self-optimizing control is a strategy for selecting controlled variables, where the economic objective guides the selection and design of controlled variables, with the expectation that maintaining the controlled variables at constant values can achieve optimization effects, translating the process optimization problem into a process control problem. Currently, self-optimizing control is widely applied to steady-state optimization problems. However, the development of process systems exhibits a trend towards refinement, highlighting the importance of optimizing dynamic processes such as batch processes and grade transitions. This paper formally introduces the self-optimizing control problem for dynamic optimization, termed the dynamic self-optimizing control problem, extending the original definition of self-optimizing control. A novel concept, "dynamic controlled variables" (DCVs), is proposed, and an implicit control policy is presented based on this concept. The paper theoretically analyzes the advantages and generality of DCVs compared to explicit control strategies and elucidates the relationship between DCVs and traditional controllers. Moreover, this paper puts forth a data-driven approach to designing self-optimizing DCVs, which considers DCV design as a mapping identification problem and employs deep neural networks to parameterize the variables. Three case studies validate the efficacy and superiority of DCVs in approximating multi-valued and discontinuous functions, as well as their application to dynamic optimization problems with non-fixed horizons, which traditional self-optimizing control methods are unable to address. • The concept of dynamic controlled variables (DCVs) is proposed. • An implicit control policy based on DCVs is proposed. • It is theoretically proven that the implicit policy can represent the set-valued mapping. • Dynamic self-optimizing control is systematically and formally proposed for the first time. • A data-driven method for designing self-optimizing dynamic controlled variables is proposed. [ABSTRACT FROM AUTHOR]

• A meta-learning based functional continuous state space (ML-FCSS) model is built. • The ML-FCSS model uses wavelet function properties to address irregular sampling. • ML-FCSS quickly establishes reliable monitoring for new batches with limited data. • The effectiveness of the ML-FCSS monitoring is demonstrated through comparisons. In an industrial batch, it is common to produce products with different grades, so only a limited number of data are available for each grade of product. The data are also easily contaminated by external disturbances and noise. The sampling interval would be messy and irregular if contaminated samples were removed. Thus, it is difficult to build models for monitoring the corresponding process. This paper proposes a meta-learning-based functional continuous state space model for fast modeling and monitoring of multi-grade batch processes. It takes advantage of wavelet function properties to effectively handle the irregular sampling issue. In addition, the meta-learning method uses diverse historical multi-grade datasets for modeling. It rapidly establishes an efficient and reliable monitoring model for new running batches with a small number of batch data. The effectiveness of the proposed method is shown through a numerical case and an industrial case in the chemical batch process. [ABSTRACT FROM AUTHOR]

• Introduction of a control strategy for batch tablet film-coating processes. • Effective use of available process data for online control of critical variables. • Use of a dynamic process simulator to validate a decentralized PI controller. • Potential reduction in total batch processing time and energy consumption. This paper proposes a control strategy for batch tablet film-coating processes using readily available process instrumentation. Outlet air conditions (temperature and relative humidity), which impact coating quality, are controlled by the manipulation of inlet air temperature and coating spray rate. Controller design, tuning and validation rely on the use of a dynamic process simulator, calibrated using data collected from a pilot plant coating unit. The final 2 × 2 decentralized PI controller demonstrated good performance for both setpoint tracking and disturbance rejection in simulation. Additionally, controlled variable setpoints were determined to maximize plant profits considering batch duration and energy consumption as optimization criteria. For the case study considered, the total batch processing time can potentially be reduced by 40 % while simultaneously reducing energy usage by 30 %, in comparison with the more conservative fixed recipe approach typically adopted in production. [ABSTRACT FROM AUTHOR]

The pivotal factor to regulate and enhance within an operating batch is the quality process, a challenging variable to monitor online. Soft sensors offer an immediate alternative for providing real-time insights into process quality, yet persisting issues include the imbalance between process and quality measurements, noisy measurements, and the intricate 3-dimensional dynamic batch data structure. This paper introduces the Robust Semi-Supervised Dual-Attention Latent Dynamic Conditional State-Space Model (RS2DA-LDCSSM) to address these challenges for within-batch quality prediction. Given the frequent absence of quality data due to measurement inconveniences, an imputation network is embedded within the RS2DA-LDCSSM to facilitate the prediction of future quality. To prevent information distortion during data unfolding, the Attentional Sequence-to-Sequence RNN Encoder-Decoder (AS2S-RNNED) is employed to process the 3-dimensional batch data. The proposed method integrates AS2S-RNNED with a probability state-space model to filter out noisy process data and stabilize the probability prediction of quality data, extracting spatial and temporal latent data from past process and quality data while minimizing the loss in multi-step prediction. This work represents a novel approach to dynamic nonlinear batch processes through probabilistic semi-supervised learning. The RS2DA-LDCSSM is adaptable to any batch process for within-batch quality prediction, as evidenced by numerical cases demonstrating its reliability, achieving an R2 value of 0.87, surpassing comparison methods. In an industrial penicillin fermentation batch process, the RS2DA-LDCSSM exhibits remarkable robustness with a high R2 index value of 0.99 in practical quality prediction scenarios, showcasing its efficacy. • Semi-supervised model training utilizes unlabeled process data. • Separate networks are crafted for process and quality feature extraction. • The state-space model with the encoder-decoder is used to extract latent features. • A multi-step-ahead prediction learning scheme yields favorable prediction results. [ABSTRACT FROM AUTHOR]

Traditional database systems like relational databases can store data which are structured with predefined schema, but in the case of bigdata, the data comes in different formats or are collected from diverse sources. The distributed databases like not only spark querying language (NoSQL) repositories are often used in relation to bigdata analytics, but a continual updating is required in business because of the streaming data that comes from stock trading, online activities of website visitors, and from the mobile applications in real time. It will not have to delay, for some report to show up, to assess and analyse the current situation, to move forward with the next business choice. Apache Spark’s structured streaming offer capabilities for handling streaming data in a batch processing mode with faster responses compared to MongoDB which is a document-based NoSQL database. This study completes similar queries to evaluate Spark SQL and NoSQL database performance, focusing on the upsides of Spark SQL over NoSQL databases in streaming data exploration. The queries are completed with streaming data stored in a batch mode. [ABSTRACT FROM AUTHOR]