Application of machine learning for production optimization

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

Machine learning for Big Data analytics in plants.

The quick development of information and the expanding complexity of large-scale data frameworks require progressed optimization methods to guarantee tall execution, versatility, and unwavering quality. Machine learning (ML) has developed as a effective apparatus for real-time optimization, advertising the capacity to memorize from tremendous sums of information and make data-driven choices with minimal human mediation. This term paper investigates the different applications of machine learning in optimizing large-scale data frameworks in genuine time, covering perspectives such as prescient analytics, peculiarity discovery, arrange activity administration, substance conveyance optimization, security, and personalized proposal frameworks. The paper points to supply a comprehensive outline of how machine learning can be utilized to upgrade the productivity, adaptability, and flexibility of these complex frameworks.

Over the past years there has been a surge of interest on the application of machine learning, and more broadly, artificial intelligence, to scientific applications. This interest has been spurred by an advancement of our computational capabilities coupled with the development of a large set of methods and machine learning frameworks to carry out complex analysis of large datasets in ways that were not possible in the past. In this presentation, I will explore the application of machine learning techniques to the area of atomic layer deposition, and in particular to process optimization. While most ALD processes are highly reproducible, the optimization of both new and existing ALD processes in novel reactors is often time consuming and labor intensive. This motivated us to search for ways of accelerating this task using both ex-situ and in-situ experimental data that is readily available in many laboratories.First, I will focus on the development of surrogate models that can predict the saturation dose times based on partially saturated growth profiles, a type of data that is part of the routine characterization of ALD processes in many labs. In order to develop this surrogate model, we first created a dataset using simulated data providing growth profiles across one of our ALD reactors for a wide range of possible experimental conditions, including precursor pressure, surface reactivity, growth per cycle, flow conditions, and dose times. We then used this dataset to train deep neural networks to predict the dose time that would lead to complete saturation. By tailoring the complexity of the model, the number of growth profiles per condition, and the structure/depth of the neural network we can explore the minimum number experiments and data points required to accurately predict saturation for an unknown ALD process. Our results show that for the optimization of a single precursor, neural networks can accurately predict saturation times using just a single growth profile and its corresponding dose time as an input.Then, I will focus on the use of in-situ techniques for the automatic optimization of ALD processes without a human in the loop. The advantage of using in-situ techniques is that they can provide a much faster response, reducing optimization times by more than two orders of magnitude. Using a realistic model of a single quartz crystal microbalance, we have developed both expert systems and Bayesian optimization-based models that are capable of exploring the process conditions and converge on optimal conditions leading to saturation. We then implemented the expert system model in one of our experimental reactors, experimentally validating this approach. This methodology can be expanded to other in-situ techniques, such as spectroscopic ellipsometry, or more sophisticated arrangement including more than one probe to obtain spatially dependent data.Finally, I will briefly discuss other potential applications of machine learning, for instance for process optimization using spatial ALD configurations, or to predict the self-limited nature of novel processes.This material is based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357.

Background and Context Computational thinking (CT) has been increasingly added to K-12 curricula, prompting teachers to grade more and more CT artifacts. This has led to a rise in automated CT assessment tools. Objective This study examines the scope and characteristics of publications that use machine learning (ML) approaches to assess students’ CT competencies from four perspectives: the educational context in which the assessments were implemented, the data used to train and validate ML algorithms, the specific ML algorithms used, and the aspects of CT assessed. Method The PRISMA approach and Arksey and O’Malley’s methodological framework for scoping reviews were adopted to search and screen studies. Findings ML algorithms have been increasingly used to assess CT competencies. However, this study identified several research gaps in the literature: existing studies were mostly conducted in the context of programming or other learning activities related to computing science; datasets used by the ML algorithms were generally small; the most frequently used algorithms were regression techniques, naive Bayes, neural networks, clustering, and natural language processing, whereas no studies used reinforcement learning; and CT competencies were not comprehensively assessed. Implications The applications of ML in CT assessments have the potential to enable personalized learning, improve assessment validity, reduce the workload of graders, and gain insights from large datasets by uncovering complex and subtle patterns.

This paper reviews the recent developments of design optimization methods for electromagnetic devices, with a focus on machine learning methods. First, the recent advances in multi-objective, multidisciplinary, multilevel, topology, fuzzy, and robust design optimization of electromagnetic devices are overviewed. Second, a review is presented to the performance prediction and design optimization of electromagnetic devices based on the machine learning algorithms, including artificial neural network, support vector machine, extreme learning machine, random forest, and deep learning. Last, to meet modern requirements of high manufacturing/production quality and lifetime reliability, several promising topics, including the application of cloud services and digital twin, are discussed as future directions for design optimization of electromagnetic devices.

Machine learning (ML) has become a valuable tool in particle accelerator control, with growing potential for beam parameter correction. In this study, we present preliminary ML applications at HLS-II, using Lasso regression for online tune correction and a neural network (NN) for beta function simulation correction. Both models were trained with supervised learning on measured beam parameter data, while an improved genetic algorithm optimized the NN structure. Our results show that the ML-based approach achieves competitive correction quality with fewer steps, making it a promising method for future particle accelerator applications and other fields.

With the rise of tall buildings, elevators have become an indispensable part. With the acceleration of urbanization and the continuous growth of population, the number of high-rise buildings is increasing, and people's demand for elevators is also growing. The safety, reliability, comfort and efficiency of elevators directly affect people's daily life and work. Therefore, how to optimize elevator PLC (Programmable Logic Controller) control system through intelligent computing and machine learning technology to improve elevator performance and user experience is a hot issue in current research. In this paper, the PLC control system is analyzed, and the method of intelligent computing and machine learning is proposed to improve the system. This paper mainly uses the experimental method and the comparison method to compare the performance of the five signal control aspects of the control system and the performance of the algorithm. The experimental results show that the maximum throughput is the neural network, and the control system under this algorithm has the lowest response time (0.4s), the highest availability (98.95%), the lowest failure rate (0.005%) and the highest security (99.995%).

Heating, ventilation and air-conditioning (HVAC) accounts for around 40% of the total building energy consumption. It has therefore become a major target for reductions, in terms of both energy usage and CO2 emissions. In the light of progress in building intelligence and energy technologies, traditional methods for HVAC optimization, control, and fault diagnosis will struggle to meet essential requirements such as energy efficiency, occupancy comfort and reliable fault detection. Machine learning and data science have great potential in this regard, particularly with developments in information technology and sensor equipment, providing access to large volumes of high-quality data. There remains, however, a number of challenges before machine learning can gain widespread adoption in industry. This review summarizes the recent literature on machine learning for HVAC system optimization, control and fault detection. Unlike other reviews, we provide a comprehensive coverage of the applications, including the factors considered. A brief overview of machine learning and its applications to HVAC is provided, after which we critically appraise the recent literature on control, optimization and fault diagnosis and detection. Finally, we provide a comprehensive discussion on the limitations of current research and suggest future research directions.

BackgroundDespite the interest in machine learning (ML) algorithms for analyzing real-world data (RWD) in healthcare, the use of ML in predicting time-to-event data, a common scenario in clinical practice, is less explored. ML models are capable of algorithmically learning from large, complex datasets and can offer advantages in predicting time-to-event data. We reviewed the recent applications of ML for survival analysis using RWD in healthcare.MethodsPUBMED and EMBASE were searched from database inception through March 2023 to identify peer-reviewed English-language studies of ML models for predicting time-to-event outcomes using the RWD. Two reviewers extracted information on the data source, patient population, survival outcome, ML algorithms, and the Area Under the Curve (AUC).ResultsOf 257 citations, 28 publications were included. Random survival forests (N = 16, 57%) and neural networks (N = 11, 39%) were the most popular ML algorithms. There was variability across AUC for these ML models (median 0.789, range 0.6–0.950). ML algorithms were predominately considered for predicting overall survival in oncology (N = 12, 43%). ML survival models were often used to predict disease prognosis or clinical events (N = 27, 96%) in the oncology, while less were used for treatment outcomes (N = 1, 4%).ConclusionsThe ML algorithms, random survival forests and neural networks, are mainly used for RWD to predict survival outcomes such as disease prognosis or clinical events in the oncology. This review shows that more opportunities remain to apply these ML algorithms to inform treatment decision-making in clinical practice. More methodological work is also needed to ensure the utility and applicability of ML models in survival outcomes.

e17570 Background: Ovarian cancer(OC) is the leading cause of death from gynecologic malignancy. Current challenges include lack of diagnostic tools, predictive biomarkers, and identifying appropriate surgical candidates. Machine learning(ML) is an emerging field that can make accurate projections by making inferences on data and may play a crucial role in OC.The objective of the current study was to review the literature on application of ML in OC and report the most commonly used algorithms and their performance in comparison to existing prediction tools and traditional regression models. Methods: This is a systematic review of published literature from January 1985 to March 2021 on the use of ML in OC. An extensive search of electronic library databases was conducted. Four independent reviewers screened the articles initially by title then full text. Quality was assessed using the MINORS criteria. P-values were generated using the Pearson’s Chi-squared(x2) test to compare performance of ML models with traditional statistics. No p-values were reported if only one study was available. Results: Among 4,295 articles screened, 88 studies on ML in OC were included. The mean age of OC patients was 54.7 years(11-90) and the most common stages at diagnosis were:Stage III (39.9%) and IV (34%). Applications of ML were in clinical datasets(33%, n = 29), preoperative diagnostics(30.7%, n = 27), serum biomarkers (21.6%, n = 19), genomics (12.5%, n = 11), and prediction of cytoreductive outcomes (2.3%, n = 2). The most commonly applied algorithms were Support Vector Machine [SVM](28%, n = 33)and Neural Networks[NN] (25.28%). Over the past decades, the number of publications on ML in OC increased three-fold from 20(1994-2010) to 67 (2011–2021). Only 9 (10%) studies compared ML techniques with existing prediction tools, or traditional regression models. Among 29 clinical dataset studies, 4 compared ML with traditional logistic regression(LR). Two studies reported better performance with ML compared to LR but not significant(accuracy: 0.88 vs 0.84, p = 0.15), one study performed comparably(accuracy: 0.1 vs 0.1) while one study performed worse(accuracy: 0.1 vs 0.97). Only one preoperative diagnostic study compared ML techniques with LR. SVM classifiers outperformed LR in classifying ovarian masses as benign or malignant(sensitivity: 0.88 vs. 0.70). One serum biomarker study compared LR with ML algorithms; LR performed better using two biomarkers for predicting OC(accuracy: 0.97 vs. 0.94). Among five studies reporting overall survival outcomes, only one study compared survival ML techniques using NN with LR and showed that NN classifiers outperformed LR in predicting overall survival(AUC: 0.72 vs. 0.62). Conclusions: This is the first systematic review exploring the literature on ML algorithms in OC. Most ML models outperformed traditional models. However, larger datasets would be required to validate findings.

Machine learning is known as the most popular methodology to do prediction on large data set while NBA’s data sets consists of plentiful statistics. Since predictions of various events are important, our research would investigate whether machine learning algorithms are efficient in doing prediction on certain NBA data sets and tasks. We are focus on mainly three supervised tasks, namely: All-Star Prediction, Playoff Prediction and Hot Streak Fallacy. For Playoff Prediction, we predict the team performance by doing machine learning on two data sets consisting of distinct well-selected features and compare the result to show which data set are more suitable for the machine learning to work. The results show that advanced statistics outperform the elementary ones. For Hot Streak Fallacy, we build the model based on multiple-linear regression to address the question: is hot streak a fallacy? It turns out that there is a lack of evidence to support ’Hot Streak Phenomenon’. For the NBA Trend, we try to view how the games involve for the past decade, and analyze the correlation of playoff tickets and other data.

Recently, the field of polymer nanocomposites has been an area of high scientific and industrial attention due to noteworthy improvements attained in these materials, arising from the synergetic combination of properties of a polymeric matrix and an organic or inorganic nanomaterial. The enhanced performance of those materials typically involves superior mechanical strength, toughness and stiffness, electrical and thermal conductivity, better flame retardancy and a higher barrier to moisture and gases. Nanocomposites can also display unique design possibilities, which provide exceptional advantages in developing multifunctional materials with desired properties for specific applications. On the other hand, machine learning (ML) has been recognized as a powerful predictive tool for data-driven multi-physical modelling, leading to unprecedented insights and an exploration of the system’s properties beyond the capability of traditional computational and experimental analyses. This article aims to provide a brief overview of the most important findings related to the application of ML for the rational design of polymeric nanocomposites. Prediction, optimization, feature identification and uncertainty quantification are presented along with different ML algorithms used in the field of polymeric nanocomposites for property prediction, and selected examples are discussed. Finally, conclusions and future perspectives are highlighted.

This research aims to develop a novel mathematical formulation of fixed point theorems in G-metric vector spaces and explore its applications in machine learning and optimization algorithms. The study begins by defining a complete G-metric space and establishing a generalized contraction condition for an operator representing iterative updates in optimization processes. Utilizing gradient descent with regularization as a case study, a numerical example is presented to validate the proposed formulation. The methodology involves iterative calculations demonstrating the convergence of a sequence of parameters toward a fixed point, highlighting the effectiveness of the auxiliary function in promoting sparsity while accommodating the non-Euclidean characteristics of high-dimensional data. The main results reveal that the proposed framework not only enhances the convergence properties of iterative algorithms but also aligns well with contemporary regularization techniques in machine learning. The conclusions drawn emphasize the significance of integrating generalized G-metric spaces and auxiliary functions in fixed point theories, suggesting that this approach provides a robust foundation for developing adaptive optimization algorithms. The findings indicate substantial implications for future research, highlighting the need for broader exploration of G-metric spaces and their applicability in various machine learning paradigms to address complex data challenges.

The application of machine learning and nature-inspired optimization methods, like for example genetic algorithms (GA) and particle swarm optimization (PSO) can be found in various scientific/technical areas. In recent years, these approaches are finding application in accelerator physics to a greater extent. In this paper, nature-inspired optimization as well as the machine learning will be shortly introduced and their application to the accelerator facility at GSI/FAIR will be presented. For the heavy-ion synchrotron SIS18 at GSI, the multi-objective GA/PSO optimization resulted in a significant improvement of multi-turn injection performance and subsequent transmission for intense beams. An automated injection optimization with genetic algorithms at the CRYRING@ESR ion storage ring has been performed. The usage of machine learning for a beam diagnostic application, where reconstruction of space-charge distorted beam profiles from ionization profile monitors is performed, will also be shown. First results and the experience gained will be presented.