Processes

Research

Jump to: Review

18 pages, 3054 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Integrating Local and Global Features for Wafer Defect Pattern Classification via Sequential Hybrid Architecture

by Jaeho Song, Seungmin Oh, Juhyeon Noh, Minsoo Hahn and Jinsul Kim

Processes 2026, 14(7), 1134; https://doi.org/10.3390/pr14071134 - 31 Mar 2026

Viewed by 739

Abstract

Wafer map defect pattern classification supports quality monitoring in semiconductor manufacturing, but public benchmark datasets such as WM-811K exhibit extreme class imbalance, where majority classes can dominate standard metrics. This study aims to improve minority class performance while maintaining inference efficiency. Building on [...] Read more.

Wafer map defect pattern classification supports quality monitoring in semiconductor manufacturing, but public benchmark datasets such as WM-811K exhibit extreme class imbalance, where majority classes can dominate standard metrics. This study aims to improve minority class performance while maintaining inference efficiency. Building on an iFormer-based hybrid backbone, we propose the Pattern-Selective Sequential Hybrid Network (PSS-HNet), which redesigns attention blocks to sequentially integrate local interaction (Modulated Convolution) and global interaction (Modulated Axial Attention) and applies sigmoid-based gating to control contextual information injection. Experiments on WM-811K (9 classes) compare iFormer (baseline), Axial-only, Axial+Modulation, and PSS-HNet using macro-averaged metrics as primary indicators, along with class-wise analysis and efficiency evaluation. PSS-HNet improves Macro-Recall by 1.02 percentage points (from 0.8852 to 0.8954) and Macro-F1 by 0.54 percentage points (from 0.9044 to 0.9098) over the baseline while maintaining similar accuracy. It also reduces computational cost and inference latency to 0.754 G FLOPs, 4.381 M parameters, and 7.682 ms, compared with 1.103 G FLOPs, 6.245 M parameters, and 8.666 ms for the baseline. Overall, selective sequential local–global integration provides a favorable balance between minority class performance and efficiency. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

20 pages, 1131 KB

Open AccessArticle

Imbalance-Aware APS Failure Classification Using Feature-Wise Attention Graph Convolutional Network

by Juhyeon Noh, Jihoon Lee, Seungmin Oh, Jaehyung Park, Minsoo Hahn, HoYong Ryu and Jinsul Kim

Processes 2026, 14(7), 1107; https://doi.org/10.3390/pr14071107 - 29 Mar 2026

Viewed by 713

Abstract

Industrial equipment data often exhibit high dimensionality and class imbalance, which make it difficult to achieve both accurate failure detection and identification of the factors contributing to failures. To address this issue, this study proposes an explainable failure classification framework, Feature-Wise Attention Graph [...] Read more.

Industrial equipment data often exhibit high dimensionality and class imbalance, which make it difficult to achieve both accurate failure detection and identification of the factors contributing to failures. To address this issue, this study proposes an explainable failure classification framework, Feature-Wise Attention Graph Convolutional Network (FWA-GCN), which combines Feature-Wise Attention (FWA) with a Graph Convolutional Network (GCN) to provide both high classification performance and variable-level interpretability. In the proposed model, tabular sensor records are treated as nodes, and a similarity-based graph is constructed to capture relationships among samples. Feature-Wise Attention learns the importance of each feature and reweights node features accordingly, and the reweighted features are then used as input to the GCN to classify failure occurrences. To alleviate the class imbalance problem, a weighted loss function is applied during training by assigning a higher weight to the failure class. Experiments conducted on the Air Pressure System (APS) dataset demonstrate that the proposed FWA-GCN achieves Precision of 79.95%, Recall of 85.07%, and F1-score of 82.43%, outperforming conventional machine learning models including Random Forest, XGBoost, CatBoost, and Multi-Layer Perceptron, as well as a standard GCN model. Furthermore, an ablation study was conducted by removing the top features selected by the attention mechanism. The results show a significant decrease in recall, confirming the effectiveness of the attention-based feature importance and supporting the interpretability of the proposed framework. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

12 pages, 710 KB

Open AccessArticle

FTIR-Based Machine Learning Identification of Virgin and Recycled Polyester for Textile Recycling in Industry 4.0

by Maria Inês Barbosa, Ana Margarida Teixeira, Maria Leonor Sousa, Pedro Ribeiro, Clara Sousa and Pedro Miguel Rodrigues

Processes 2026, 14(6), 964; https://doi.org/10.3390/pr14060964 - 18 Mar 2026

Cited by 1 | Viewed by 1036

Abstract

Advances in Industry 4.0 manufacturing have accelerated the adoption of machine learning (ML) for automated classification. Polyester (PES), a widely used synthetic fiber, competes with natural fibers like cotton and other synthetics, highlighting the need for continuous research and improvement. In the textile [...] Read more.

Advances in Industry 4.0 manufacturing have accelerated the adoption of machine learning (ML) for automated classification. Polyester (PES), a widely used synthetic fiber, competes with natural fibers like cotton and other synthetics, highlighting the need for continuous research and improvement. In the textile sector, distinguishing recycled polyester (rPES) from virgin polyester (vPES) remains challenging due to overlapping chemical signatures and material variability. A combination of Fourier transform infrared (FTIR) spectroscopy and ML has not been explored for this purpose. In this study, we evaluated ML models to discriminate three PES fiber types (45 vPES, 65 rPES, and 55 mixed PES) using 165 FTIR spectra across four spectral regions, R1, R2, R3, and R4, as well as their combined representation. Six ML approaches were tested on data reduced with fast independent component analysis (FastICA) (1–30 components) using an 80/20 train–test dataset split. The Decision Tree classifier achieved the highest Accuracy in four of the five spectral evaluations, with classification accuracies ranging from 66.67% to 77.78% for region R4, which also had a balanced classification profile with an area-under-the-curve (AUC) value of 0.81. Notably, despite the moderate overall Accuracy, the model achieved 100% discrimination of rPES when distinguishing it from both mixed and vPES. Mixed fibers remained the most difficult to classify, highlighting the need for improved feature representation. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

14 pages, 2460 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Generating Synthetic Data from Real-Time Simulators for Deep Learning Modeling of Machining

by Giambattista Gruosso and Enrico Spateri

Processes 2025, 13(12), 3953; https://doi.org/10.3390/pr13123953 - 7 Dec 2025

Cited by 3 | Viewed by 1587

Abstract

Manufacturers of cutting and machining machines face increasing pressure to optimize performance and sustainability while complying with evolving regulations. Traditional machine learning approaches are often limited by biased and repetitive datasets collected during real operations. This article presents a real-time simulation framework for [...] Read more.

Manufacturers of cutting and machining machines face increasing pressure to optimize performance and sustainability while complying with evolving regulations. Traditional machine learning approaches are often limited by biased and repetitive datasets collected during real operations. This article presents a real-time simulation framework for generating large synthetic datasets to train predictive machining models. A mechanistic model with probabilistic parameters is validated on experimental data and integrated into the simulator, enabling neural networks to predict process metrics such as vibrations, cutting forces, and product quality prior to machining. The framework further supports large-scale optimal control by testing setpoint control strategies for virtual prototyping. This approach allows manufacturers to enhance efficiency, reduce waste, and improve product quality while minimizing operational risks. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

19 pages, 21045 KB

Open AccessArticle

Performance of Machine Learning Algorithms in Fault Diagnosis for Manufacturing Systems: A Comparative Analysis

by Abner B. Montejano Leija, Elvia Ruiz Beltrán, Jorge L. Orozco Mora and Jorge O. Valdés Valadez

Processes 2025, 13(6), 1624; https://doi.org/10.3390/pr13061624 - 22 May 2025

Cited by 10 | Viewed by 7085

Abstract

This study presents a comparative analysis of various machine learning algorithms to evaluate their performance in diagnosing faults within automated manufacturing systems. The primary objective is to identify the most effective model for classifying equipment failures based on historical data. Several algorithms were [...] Read more.

This study presents a comparative analysis of various machine learning algorithms to evaluate their performance in diagnosing faults within automated manufacturing systems. The primary objective is to identify the most effective model for classifying equipment failures based on historical data. Several algorithms were selected, including support vector machines (SVM), Decision trees, boosting, random forest, k-nearest neighbors (KNN), stacking, and artificial neural networks. The research began with the collection of a dataset using an Arduino-based system with sensors (temperature, electrical current, differential pressure, vibration, and sound) to monitor the equipment’s operational condition. Faults were intentionally induced in a motor, an electrovalve, and a pneumatic cylinder. The data were then processed in a Python environment, undergoing normalization and dimensionality reduction. The models were evaluated through cross-validation and compared using metrics such as precision, recall, F1-score, and accuracy. Results indicated that all models performed well, with the SVM algorithm showing the best overall performance, with an average fault diagnosis accuracy of 91.62% when trained on the full dataset and 66.83% under extreme class imbalance. In contrast, decision trees demonstrated lower generalization ability. This study provides insights for future fault diagnosis research using machine learning and offers recommendations for implementing such technologies in industrial environments. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

21 pages, 5000 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Surrogate-Based Multidisciplinary Optimization for the Takeoff Trajectory Design of Electric Drones

by Samuel Sisk and Xiaosong Du

Processes 2024, 12(9), 1864; https://doi.org/10.3390/pr12091864 - 31 Aug 2024

Cited by 8 | Viewed by 2707

Abstract

Electric vertical takeoff and landing (eVTOL) aircraft attract attention due to their unique characteristics of reduced noise, moderate pollutant emission, and lowered operating cost. However, the benefits of electric vehicles, including eVTOL aircraft, are critically challenged by the energy density of batteries, which [...] Read more.

Electric vertical takeoff and landing (eVTOL) aircraft attract attention due to their unique characteristics of reduced noise, moderate pollutant emission, and lowered operating cost. However, the benefits of electric vehicles, including eVTOL aircraft, are critically challenged by the energy density of batteries, which prohibit long-distance tasks and broader applications. Since the takeoff process of eVTOL aircraft demands excessive energy and couples multiple subsystems (such as aerodynamics and propulsion), multidisciplinary analysis and optimization (MDAO) become essential. Conventional MDAO, however, iteratively evaluates high-fidelity simulation models, making the whole process computationally intensive. Surrogates, in lieu of simulation models, empower efficient MDAO with the premise of sufficient accuracy, but naive surrogate modeling could result in an enormous training cost. Thus, this work develops a twin-generator generative adversarial network (twinGAN) model to intelligently parameterize takeoff power and wing angle profiles of an eVTOL aircraft. The twinGAN-enabled surrogate-based takeoff trajectory design framework was demonstrated on the Airbus

A^{3}

Vahana aircraft. The twinGAN provisioned two-fold dimensionality reductions. First, twinGAN generated only realistic trajectory profiles of power and wing angle, which implicitly reduced the design space. Second, twinGAN with three variables represented the takeoff trajectory profiles originally parameterized using 40 B-spline control points, which explicitly reduced the design space while maintaining sufficient variability, as verified by fitting optimization. Moreover, surrogate modeling with respect to the three twinGAN variables, total takeoff time, mass, and power efficiency, reached around 99% accuracy for all the quantities of interest (such as vertical displacement). Surrogate-based, derivative-free optimizations obtained over 95% accuracy and reduced the required computational time by around 26 times compared with simulation-based, gradient-based optimization. Thus, the novelty of this work lies in the fact that the twinGAN model intelligently parameterized trajectory designs, which achieved implicit and explicit dimensionality reductions. Additionally, twinGAN-enabled surrogate modeling enabled the efficient takeoff trajectory design with high accuracy and computational cost reduction. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

16 pages, 3200 KB

Open AccessArticle

Learning More with Less Data in Manufacturing: The Case of Turning Tool Wear Assessment through Active and Transfer Learning

by Alexios Papacharalampopoulos, Kosmas Alexopoulos, Paolo Catti, Panagiotis Stavropoulos and George Chryssolouris

Processes 2024, 12(6), 1262; https://doi.org/10.3390/pr12061262 - 19 Jun 2024

Cited by 20 | Viewed by 2672

Abstract

Monitoring tool wear is key for the optimization of manufacturing processes. To achieve this, machine learning (ML) has provided mechanisms that work adequately on setups that measure the cutting force of a tool through the use of force sensors. However, given the increased [...] Read more.

Monitoring tool wear is key for the optimization of manufacturing processes. To achieve this, machine learning (ML) has provided mechanisms that work adequately on setups that measure the cutting force of a tool through the use of force sensors. However, given the increased focus on sustainability, i.e., in the context of reducing complexity, time and energy consumption required to train ML algorithms on large datasets dictate the use of smaller samples for training. Herein, the concepts of active learning (AL) and transfer learning (TL) are simultaneously studied concerning their ability to meet the aforementioned objective. A method is presented which utilizes AL for training ML models with less data and then it utilizes TL to further reduce the need for training data when ML models are transferred from one industrial case to another. The method is tested and verified upon an industrially relevant scenario to estimate the tool wear during the turning process of two manufacturing companies. The results indicated that through the application of the AL and TL methodologies, in both companies, it was possible to achieve high accuracy during the training of the final model (1 and 0.93 for manufacturing companies B and A, respectively). Additionally, reproducibility of the results has been tested to strengthen the outcomes of this study, resulting in a small standard deviation of 0.031 in the performance metrics used to evaluate the models. Thus, the novelty presented in this paper is the presentation of a straightforward approach to apply AL and TL in the context of tool wear classification to reduce the dependency on large amounts of high-quality data. The results show that the synergetic combination of AL with TL can reduce the need for data required for training ML models for tool wear prediction. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

16 pages, 2543 KB

Open AccessArticle

Novel Triplet Loss-Based Domain Generalization Network for Bearing Fault Diagnosis with Unseen Load Condition

by Bingbing Shen, Min Zhang, Le Yao and Zhihuan Song

Processes 2024, 12(5), 882; https://doi.org/10.3390/pr12050882 - 26 Apr 2024

Cited by 9 | Viewed by 2787

Abstract

In the real industrial manufacturing process, due to the constantly changing operational loads of equipment, it is difficult to collect data from all load conditions as the source domain signal for fault diagnosis. Therefore, the appearance of unseen load vibration signals in the [...] Read more.

In the real industrial manufacturing process, due to the constantly changing operational loads of equipment, it is difficult to collect data from all load conditions as the source domain signal for fault diagnosis. Therefore, the appearance of unseen load vibration signals in the target domain presents a challenge and research hotspot in fault diagnosis. This paper proposes a triplet loss-based domain generalization network (TL-DGN) and then applies it to an unseen domain bearing fault diagnosis. TL-DGN first utilizes a feature extractor to construct a multi-source domain classification loss. Furthermore, it measures the distance between class data from different domains using triplet loss. The introduced triplet loss can narrow the distance between samples of the same class in the feature space and widen the distance between samples of different classes based on the action of the cross-entropy loss function. It can reduce the dependency of the classification boundary on bearing operational loads, resulting in a more generalized classification model. Finally, two comparative experiments with fault diagnosis models without triplet loss and other classification models demonstrate that the proposed model achieves superior fault diagnosis performance. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

24 pages, 10759 KB

Open AccessArticle

Optimization of Smart Textiles Robotic Arm Path Planning: A Model-Free Deep Reinforcement Learning Approach with Inverse Kinematics

by Di Zhao, Zhenyu Ding, Wenjie Li, Sen Zhao and Yuhong Du

Processes 2024, 12(1), 156; https://doi.org/10.3390/pr12010156 - 9 Jan 2024

Cited by 5 | Viewed by 3870

Abstract

In the era of Industry 4.0, optimizing the trajectory of intelligent textile robotic arms within cluttered configuration spaces for enhanced operational safety and efficiency has emerged as a pivotal area of research. Traditional path-planning methodologies predominantly employ inverse kinematics. However, the inherent non-uniqueness [...] Read more.

In the era of Industry 4.0, optimizing the trajectory of intelligent textile robotic arms within cluttered configuration spaces for enhanced operational safety and efficiency has emerged as a pivotal area of research. Traditional path-planning methodologies predominantly employ inverse kinematics. However, the inherent non-uniqueness of these solutions often leads to varied motion patterns in identical settings, potentially leading to convergence issues and hazardous collisions. A further complication arises from an overemphasis on the tool center point, which can cause algorithms to settle into suboptimal solutions. To address these intricacies, our study introduces an innovative path-planning optimization strategy utilizing a model-free, deep reinforcement learning framework guided by inverse kinematics experience. We developed a deep reinforcement learning algorithm for path planning, amalgamating environmental enhancement strategies with multi-information entropy-based geometric optimization. This approach specifically targets the challenges outlined. Extensive experimental analyses affirm the enhanced optimality and robustness of our method in robotic arm path planning, especially when integrated with inverse kinematics, outperforming existing algorithms in terms of safety. This advancement notably elevates the operational efficiency and safety of intelligent textile robotic arms, offering a groundbreaking and pragmatic solution for path planning in real-world intelligent knitting applications. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

17 pages, 4166 KB

Open AccessArticle

Wear Prediction of Tool Based on Modal Decomposition and MCNN-BiLSTM

by Zengpeng He, Yefeng Liu, Xinfu Pang and Qichun Zhang

Processes 2023, 11(10), 2988; https://doi.org/10.3390/pr11102988 - 16 Oct 2023

Cited by 7 | Viewed by 2638

Abstract

Metal cutting is a complex process with strong randomness and nonlinear characteristics in its dynamic behavior, while tool wear or fractures will have an immediate impact on the product surface quality and machining precision. A combined prediction method comprising modal decomposition, multi-channel input, [...] Read more.

Metal cutting is a complex process with strong randomness and nonlinear characteristics in its dynamic behavior, while tool wear or fractures will have an immediate impact on the product surface quality and machining precision. A combined prediction method comprising modal decomposition, multi-channel input, a multi-scale Convolutional neural network (CNN), and a bidirectional long-short term memory network (BiLSTM) is presented to monitor tool condition and to predict tool-wear value in real time. This method considers both digital signal features and prediction network model problems. First, we perform correlation analysis on the gathered sensor signals using Pearson and Spearman techniques to efficiently reduce the amount of input signals. Second, we use Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to enhance the local characteristics of the signal, then boost the neural network’s identification accuracy. In addition, the deconstructed signal is converted into a multi-channel input matrix, from which multi-scale spatial characteristics and two-way temporal features are recovered using multi-scale CNN and BiLSTM, respectively. Finally, this strategy is adopted in simulation verification using real PHM data. The wear prediction experimental results show that, in the developed model, C1, C4, and C6 have good prediction performance, with RMSE of 8.2968, 12.8521, 7.6667, and MAE of 6.7914, 9.9263, and 5.9884, respectively, significantly lower than SVR, B-BiLSTM, and 2DCNN models. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

Review

Jump to: Research

73 pages, 3995 KB

Open AccessReview

Generative Artificial Intelligence in Aircraft Design Optimization

by Xiaosong Du

Processes 2026, 14(4), 719; https://doi.org/10.3390/pr14040719 - 22 Feb 2026

Cited by 3 | Viewed by 4044

Abstract

Aircraft design optimization is essential for improving aircraft performance (such as reduced fuel consumption and lowered noise), which leads to more efficient, sustainable, and affordable aircraft. Conventional aircraft design adopts physics-based simulation models, but iteratively evaluating simulation models is computationally intensive, or even [...] Read more.

Aircraft design optimization is essential for improving aircraft performance (such as reduced fuel consumption and lowered noise), which leads to more efficient, sustainable, and affordable aircraft. Conventional aircraft design adopts physics-based simulation models, but iteratively evaluating simulation models is computationally intensive, or even practically impossible. Meanwhile, artificial intelligence (AI) emerges as a revolutionary game changer in the modern engineering industry, including aircraft design optimization. Generative AI (genAI), one of the groundbreaking AI methods, has been advancing aircraft design optimization from various aspects, including intelligent parameterization, predictive modeling, training facilitation, and constraints handling. However, there is a lack of a review summarizing genAI applications in aircraft design optimization. This paper encapsulates four key genAI methods (namely, variational autoencoder, generative adversarial networks, diffusion, and transformer models), followed by advantages and drawbacks, as well as crucial advancements in aircraft design. This work aims to synthesize existing knowledge, identify research gaps, and guide future research for the genAI and aircraft design optimization communities. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

40 pages, 1380 KB

Open AccessFeature PaperReview

Recent Advances in Data-Driven Methods for Degradation Modeling Across Applications

by Anna Jarosz-Kozyro and Jerzy Baranowski

Processes 2025, 13(12), 3962; https://doi.org/10.3390/pr13123962 - 8 Dec 2025

Cited by 4 | Viewed by 2437

Abstract

Understanding degradation is crucial for ensuring the longevity and performance of materials, systems, and organisms. To illustrate the similarities across applications, this article provides a review of data-based methods in materials science, engineering, and medicine. The methods analyzed in this paper include regression [...] Read more.

Understanding degradation is crucial for ensuring the longevity and performance of materials, systems, and organisms. To illustrate the similarities across applications, this article provides a review of data-based methods in materials science, engineering, and medicine. The methods analyzed in this paper include regression analysis, factor analysis, cluster analysis, Markov Chain Monte Carlo, Bayesian statistics, hidden Markov models, nonparametric Bayesian modeling of time series, supervised learning, and deep learning. The review provides an overview of degradation models, referencing books and methods, and includes detailed tables highlighting the applications and insights offered in medicine, power engineering, and material science. It also discusses the classification of methods, emphasizing statistical inference, dynamic prediction, machine learning, and hybrid modeling techniques. Overall, this review enhances understanding of degradation modeling across diverse domains. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

34 pages, 1873 KB

Open AccessReview

Artificial Intelligence in Rice Quality and Milling: Technologies, Applications, and Future Prospects

by Benjamin Ilo, Abraham Badjona, Yogang Singh, Alex Shenfield and Hongwei Zhang

Processes 2025, 13(11), 3731; https://doi.org/10.3390/pr13113731 - 19 Nov 2025

Cited by 5 | Viewed by 4372

Abstract

The global demand for high-quality rice necessitates advancements in milling technologies and quality assessment techniques that are rapid, accurate, and scalable. Traditional methods of rice evaluation are time-consuming and subjective, and are increasingly being replaced by artificial intelligence driven solutions that offer non-destructive, [...] Read more.

The global demand for high-quality rice necessitates advancements in milling technologies and quality assessment techniques that are rapid, accurate, and scalable. Traditional methods of rice evaluation are time-consuming and subjective, and are increasingly being replaced by artificial intelligence driven solutions that offer non-destructive, real-time monitoring capabilities. This review presents a comprehensive synthesis of current AI applications including machine vision, deep learning, spectroscopy, thermal imaging, and hyperspectral imaging for the assessment and classification of rice quality across various stages of processing. Major emphasis is put on the recent advances in convolutional neural networks (CNNs), YOLO architectures, and Mask R-CNN models, and their integration into industrial rice milling systems is discussed. Additionally, the review highlights next steps, notably designing lean AI architectures suitable for edge computing, hybrid imaging systems, and the creation of open-access datasets. Across recent rice-focused studies, classification accuracies for grading and varietal identification are typically ≥

90 %

using machine vision and CNNs, while NIR–ANN models for physicochemical properties (e.g., moisture/protein proxies) commonly report strong fits (

R^{2} \approx 0.90 – 0.99

). End-to-end detectors/segmenters (e.g., YOLO/YO-LACTS) achieve high precision suitable for near real-time inspection. These results indicate that AI-based approaches can substantially outperform conventional evaluation in both accuracy and throughput. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

28 pages, 3147 KB

Open AccessReview

Framework for the Strategic Adoption of Industry 4.0: A Focus on Intelligent Systems

by Joel Serey, Miguel Alfaro, Guillermo Fuertes, Manuel Vargas, Rodrigo Ternero, Claudia Duran, Jorge Sabattin and Sebastian Gutierrez

Processes 2023, 11(10), 2973; https://doi.org/10.3390/pr11102973 - 13 Oct 2023

Cited by 22 | Viewed by 11166

Abstract

Despite growing interest in smart manufacturing, there is little information on how organizations can approach the alignment of strategic processes with Industry 4.0. This study seeks to fill this knowledge gap by developing a framework for the integration of Industry 4.0 techniques and [...] Read more.

Despite growing interest in smart manufacturing, there is little information on how organizations can approach the alignment of strategic processes with Industry 4.0. This study seeks to fill this knowledge gap by developing a framework for the integration of Industry 4.0 techniques and artificial intelligence systems. This framework will serve as a conceptual guide in the digital transformation processes toward Industry 4.0. This study involved a systematic literature review of the important methodological proposals and identification of thematic axes, research topics, strategic objectives, challenges, drivers, technological trends, models, and design architectures. In total, 160 articles were selected (120 were published between 2017 and 2022). The results provide insights into the prospects for strategic alignment in the adoption of Industry 4.0. The conceptualization of the framework shows that Industry 4.0 needs strategic adjustments mainly in seven objectives (business model, change mindset, skills, human resources, service level, ecosystem, interconnection, and absorption capacity) derived from 10 thematic axes and 28 research topics. Understanding the strategic adoption of Industry 4.0 and artificial intelligence is vital for industrial organizations to stay competitive and relevant in a constantly evolving business landscape. Full article

(This article belongs to the Special Issue Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine Learning, Control, and Optimization in Manufacturing and Industry 4.0

Share This Special Issue

Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (14 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI