Manufacturing Control Research Articles

Multi-Domain Data Integration for Plasma Diagnostics in Semiconductor Manufacturing Using Tri-CycleGAN

The precise monitoring of chemical reactions in plasma-based processes is crucial for advanced semiconductor manufacturing. This study integrates three diagnostic techniques—Optical Emission Spectroscopy (OES), Quadrupole Mass Spectrometry (QMS), and Time-of-Flight Mass Spectrometry (ToF-MS)—into a reactive ion etcher (RIE) system to analyze CF4-based plasma. To synchronize and integrate data from these different domains, we developed a Tri-CycleGAN model that utilizes three interconnected CycleGANs for bi-directional data transformation between OES, QMS, and ToF-MS. This configuration enables accurate mapping of data across domains, effectively compensating for the blind spots of individual diagnostic techniques. The model incorporates self-attention mechanisms to address temporal misalignments and a direct loss function to preserve fine-grained features, further enhancing data accuracy. Experimental results show that the Tri-CycleGAN model achieves high consistency in reconstructing plasma measurement data under various conditions. The model’s ability to fuse multi-domain diagnostic data offers a robust solution for plasma monitoring, potentially improving precision, yield, and process control in semiconductor manufacturing. This work lays a foundation for future applications of machine learning-based diagnostic integration in complex plasma environments.

Strategic Innovations in Apple's Supply Chain Management: Objectives, Methods, and Strategies for Navigating Global Market Challenges

This study looks at global supply chain risks and remedies in the context of Apple Inc.'s supply chain, which is renowned for being efficient and complicated. Apple's supply chain management strategy (SCM) optimizes costs and efficiency by integrating the planning and control of manufacturing, distribution, and sales. Efficient worldwide product delivery and very high operational standards are guaranteed by centralized strategic decision-making and collaboration with key suppliers like Foxconn. The report emphasizes how Apple uses cutting-edge logistics technology to reduce risks like supply interruptions and geopolitical unrest, which are becoming more common in today's international marketplace. Additionally, the study holds that in order to gain a long-term market competitiveness and manage a more uncertain external environment, today's smart device and electronic equipment manufacturers represented by Apple need to embrace the wave of digital transformation and increase resilience through strategic innovation and the construction of ethical and sustainable supply chains. This entails building morally and environmentally sound supply networks as well as implementing strategic innovations that increase supply chain resilience. Businesses that use this approach not only mitigate short-term risks but also establish a strong basis for sustained prosperity, guaranteeing their ability to adjust and prosper in the dynamic international arena.

Learning-based production, maintenance, and quality optimization in smart manufacturing systems: A literature review and trends

With the introduction of manufacturing paradigms, including Industry 4.0, production research has shifted its focus to enabling intelligent manufacturing systems within industrial environments. These systems can efficiently schedule and control processes and operations using artificial intelligence methods, including machine learning and deep learning. Since 1995, relevant literature has presented several examples of such implementations, addressing topics, for example equipment fault diagnosis and quality inspections. To this end, the present paper strives to present a state-of-the-art review of the learning-based scheduling and control frameworks, which are exploited in the production research. The review is limited to the relevant research between the years 1995 and 2024, surveying approaches in the domains of manufacturing, maintenance, and quality control. To this end, the paper follows a meta-analysis method for the selection and evaluation of relevant research articles. Moreover, research questions are formulated to analyze the obtained findings and seek out insights on aspects of the relevant research, including the inclusion of decision-making models and dissemination of literature. The provided answers, among others, reveal trends and limitations of the state-of-the art research in relation to learning-based scheduling and control.

AI-Driven Quality Control in PCB Manufacturing: Enhancing Production Efficiency and Precision

This paper investigates the application of Artificial Intelligence (AI) in enhancing quality control within Printed Circuit Board (PCB) manufacturing processes, focusing on how AI-driven technologies improve production efficiency and precision. The research addresses traditional quality control methods, such as manual inspection and Automated Optical Inspection (AOI), highlighting their limitations in keeping up with the complexities and demand for high-precision PCBs in modern electronics. The study delves into how AI technologies, particularly machine learning, computer vision, and predictive analytics, are being leveraged to overcome these limitations. By automating defect detection, improving accuracy, and enabling real-time analysis, AI systems not only streamline the quality control process but also significantly reduce human error and production costs. AI-driven quality control systems are shown to increase defect detection rates, reduce inspection times, and enhance overall production throughput. The paper includes a comparative analysis between traditional and AI-based quality control methods, revealing a notable improvement in both detection accuracy and production speed when AI systems are employed. Additionally, cost efficiency is explored, demonstrating how AI systems reduce waste, minimize rework, and lower operational costs. The potential challenges of AI implementation, such as the high initial costs, data requirements, and integration with legacy systems, are also discussed. The paper concludes that despite these challenges, AI offers a transformative solution to the growing demands of the PCB manufacturing industry, with the ability to scale effectively and adapt to future technological advancements. Ultimately, this research underscores the significant role of AI in revolutionizing PCB quality control by providing a more efficient, precise, and cost-effective approach, paving the way for further innovation in the electronics manufacturing sector.

Knowledge graph-enhanced multi-agent reinforcement learning for adaptive scheduling in smart manufacturing

AbstractSelf-organizing manufacturing network has emerged as a viable solution for adaptive manufacturing control within the mass personalization paradigm. This approach involves three critical elements: system modeling and control architecture, interoperable communication, and adaptive manufacturing control. However, current research often separates interoperable communication from adaptive manufacturing control as isolated areas of study. To address this gap, this paper introduces Knowledge Graph-enhanced Multi-Agent Reinforcement Learning (MARL) method that integrates interoperable communication via Knowledge Graphs with adaptive manufacturing control through Reinforcement Learning. We hypothesize that implicit domain knowledge obtained from historical production job allocation records can guide each agent to learn more effective scheduling policies with accelerated learning rates. This is based on the premise that machine assignment preferences effectively could reduce the Reinforcement Learning search space. Specifically, we redesign machine agents with new observation, action, reward, and cooperation mechanisms considering the preference of machines, building upon our previous MARL base model. The scheduling policies are trained under extensive simulation experiments that consider manufacturing requirements. During the training process, our approach demonstrates improved training speed compared with individual Reinforcement Learning methods under the same training hyperparameters. The obtained scheduling policies generated by our Knowledge Graph-enhanced MARL also outperform both individual Reinforcement Learning methods and heuristic rules under dynamic manufacturing settings.

Ergot alkaloid control in biotechnological processes and pharmaceuticals (a mini review).

The control of ergot alkaloids in biotechnological processes is important in the context of obtaining new strain producers and studying the mechanisms of the biosynthesis, accumulation and secretion of alkaloids and the manufacturing of alkaloids. In pharmaceuticals, it is important to analyze the purity of raw materials, especially those capable of racemization, quality control of dosage forms and bulk drugs, stability during storage, etc. This review describes the methods used for qualitative and quantitative chemical analysis of ergot alkaloids in tablets and pharmaceutic forms, liquid cultural media and mycelia from submerged cultures of ergot and other organisms producing ergoalkaloid, sclerotias of industrial Claviceps spp. parasitic strains. We reviewed analytical approaches for the determination of ergopeptines (including their dihydro- and bromine derivatives) and semisynthetic ergot-derived medicines such as cabergoline, necergoline and pergolide, including precursors for their synthesis. Over the last few decades, strategies and approaches for the analysis of ergoalkaloids for medical use have changed, but the general principles and objectives have remained the same as before. These changes are related to the development of new genetically improved strains producing ergoalkaloids and the development of technologies for the online control of biotechnological processes and pharmaceutical manufacturing ("process analytical technologies," PAT). Overall, the industry is moving toward "smart manufacturing." The development of approaches to production cost estimation and product quality management, manufacturing management, increasing profitability and reducing the negative impact on personnel and the environment are integral components of sustainable development. Analytical approaches for the analysis of ergot alkaloids in pharmaceutical raw materials should have high enough specificity for the separation of dihydro derivatives, enantiomers and R-S epimers of alkaloids, but low values of the quantitative detection limit are less frequently needed. In terms of methodology, detection methods based on mass spectrometry have become more developed and widespread, but NMR analysis remains in demand because of its high accuracy and specificity. Both rapid methods and liquid chromatography remain in demand in routine practice, with rapid analysis evolving toward higher accuracy owing to improved analytical performance and new equipment. New composite electrochemical sensors (including disposable sensors) have demonstrated potential for real-time process control.

Mass balance analysis for therapeutic peptides: Case studies, applications, and perspectives

The concept of mass balance is discussed as it pertains to the pharmaceutical development of therapeutic peptides. Case studies are presented demonstrating how to perform a mass balance assessment on solid drug substance and solution drug product, and the role of mass balance in the context of the overall product control strategy is discussed. Utilizing mass balance as a specification test where the result is calculated from other critical quality attribute tests, each with their own specification, offers little value as a formalized quality acceptance criterion and may create more deviations, non-value added investigations, and potential batch failures. While useful in characterizing the performance of analytical methods and as part of a rigorous understanding of the manufacturing process and control strategy development, mass balance should not be required as a specification control and should instead be demonstrated during method development and through well-designed forced degradation experiments. Analytical method variability is discussed in relation to the analytical target profile, and the overall impact of sources of variability on the mass balance calculation is described in support of this position.

Moisture content determination along production line of ibuprofen soft gelatin capsule manufacturing by near infrared spectroscopy and ensemble deep neural networks

AbstractIn the manufacturing process of ibuprofen soft gelatin capsules, controlling moisture content at each production line stage, including in their components—gelatin, fill content, and shell—is vital to ensure quality and stability. This study developed and assessed an analytical method for rapid and non‐destructive moisture determination using near‐infrared spectroscopy (NIRS) coupled with deep neural networks (DNN) on all stages of the ibuprofen production line. The NIRS‐DNN classifier models were able to distinguish between the three components, achieving accuracy scores of up to 99%. The DNN models for moisture quantification also demonstrated high accuracy, with R2 values exceeding 0.997 across all production stages and prediction errors to those of previously reported models. A significant advantage of the NIRS‐DNN approach was its ability to maintain accuracy over a wide moisture concentration range, from 7% to 48%. The ensemble model, NIRS‐EDNN, seamlessly integrated classification and quantification, revealing its potential for real‐time process control in soft gel manufacturing. The comprehensive sampling approach ensured a diverse representation of moisture content, thereby enhancing the understanding of its impact on the final product stability, demonstrating that this methodology is potentially applicable to any soft gelatin capsule tracking worldwide.

Numerical simulation for microstructure control in wire arc additive manufacturing of thin-walled structures

The difference of cooling rates on the surface and the interior of thin-walled structures leads to significant differences of microstructures in additive manufacturing (AM). To reveal the microstructure control in wire arc additive manufacturing of thin-walled structures, a gas-heat coupling model with experimental validation is proposed. The computational accuracy can reach 96% in prediction of temperatures and microstructures. Increasing the preheating or scanning speed leads to a higher probability of heterogeneous nucleation on the surface of thin-walled structures. When the pre-heating is increased from 550 K to 750 K, the proportion of equiaxed grains increases by 20.8%. When the gas flow rate of super cooling is increased from 20 L/min to 30 L/min, the size of equiaxed grains is decreased from 0.33 mm to 0.23 mm on the surface, and the width of columnar grains is decreased from 0.53 mm to 0.42 mm in the interior. This is due to the significant differences in cooling rates in thin-walled structures.

Comprehensive Assessment of Deep-Water Vessel Implosion Mechanisms: OceanGate's Titan Submersible Failure Sequence Explained

This study outlines the physical mechanisms involved in a submersible implosion and analyzes the loss of the Titan submersible (‘sub’) that occurred on 18 June 2023 during a mission to visit the wreck of the Titanic. Titan’s collapse mechanisms at the moment of implosion are described in detail and outer hull fracturing rate, subsequent implosion rate, accompanying heat release and other key processes are quantified. Plausible causes of the hull’s leak leading up to critical loss of the sub's hermetic closure are reviewed using test results made publicly available by the U.S. Marine Board of Investigation. Their data indicated that the bond interfaces between the individual layers of the carbon fiber hull (Hull V2) were critically compromised due to manufacturing defects, voids, porosity, and inadequate adhesive integrity, resulting in significant delamination. Analysis of data from the real-time hull health monitoring system, revealed acoustic anomalies and strain shifts, pointing toward increasing structural fatigue, which went unaddressed prior to the fatal dive. The implosion process can be characterized by an instantaneous collapse of the air volume within the hull under extreme external pressure: even the tiniest leak would lead to destruction of the vessel's structural integrity. The destruction was the more devastating, because it was accompanied by a secondary explosion due to the heat exchange between the collapsing air volume and the ambient sea water. While the collapsing air was phase-changed into a supercritical state, the generated heat caused the adjacent seawater to evaporate and expand. Hull pieces fragmented by the initial implosion were strewn around during the secondary explosion phase, which ceased rapidly as the steam condensed back into seawater once again. The Titan incident underscores the urgent need for improved design standards, rigorous quality control in manufacturing, and enhanced real-time monitoring to prevent similar failures of future deep-sea exploration vehicles.

Biomechanical considerations of chemical structure and biosafety of current ceramic biomaterials for dentistry: review and outlook of the current state of the art.

Biomaterial refers to any material, non-pharmaceutical or combination of substances of synthetic or natural origin used for any period independently or as part of a system for the purpose of healing, assisting the growth or replacement of tissues, organs or functions of the body. It is an unsustainable material that interacts with biological systems. Before being produced a biomaterial goes through a sequence of steps, which includes: 1) the definition of the problem that the material will be called to solve (treatment, replacement of the instrument, aesthetic reasons); 2) design of the device, composition and control of materials (mechanical properties, toxicity, biological response, corrosion resistance, interaction with proteins, cells and tissues), manufacture, sterilization and standardization; 3) control of the device (in experimental animals, in vitro) clinical studies, studies; and 4) monitor its long-term use in vivo, in vitro and in patients. Research for ceramic materials is evolving and because they can be porous or glassy, they find applications in medicine and biotechnology, as they can be used as fillers, covering materials and scaffolds. Therefore, ceramic biomaterials are widely used not only in the field of orthopedic and maxillofacial surgery but also in dentistry as for dental prostheses. Materials monitoring technologies allow us to monitor the three-dimensional development in space, as well as imperfections or micro-cracks in the ceramic.

Attention Pyramid Dilated Region-based Model for Metallurgical Defect Detection

Abstract Defect recognition is the key to realizing automatic visual inspection and quality control in intelligent manufacturing. Deep learning (DL) has been widely applied to locate damaged areas in images, characterize impurities of materials and further analyze the quality of products. However, automatic defect detection by DL in practical industrial applications is still a challenge due to the lack of sufficient datasets and appropriate recognition methods. Here, a novel Attention Pyramid Dilated Region-based Convolutional Neural Network (ADRCNN) is proposed to realize the multi-scale defect recognition and pixel-level instance segmentation of metallographic images. We also collected a dataset containing 900 images of commercial A356 aluminum alloy with different casting defects. The ADRCNN model is evaluated on our dataset with an average detection accuracy of 87.2% and 93.3% on validation and test sets respectively. To address the overfitting problem, a pretraining fine-tuning strategy is implemented by using the pretraining weights from large-scale datasets and temporarily freezing the weights of the backbone network during the training process. The experimental results show that the proposed model can achieve satisfactory defect segmentation in metallographic images, promoting the development of intelligent manufacturing in alloy industries.

Extension of paperboard modelling with Föppl–von Karman terms for improved stress state under suction pressure

A practical method for solving the bending stiffness of a thin orthotropic plate based on measured deflection and known loading was studied. The target application was paperboard manufacturing and related process control. Here, finite element (FE) method was used to create virtual paperboard and its deflection data. The accuracy of the linear Kirchhoff plate model used in the practical method was tested against the FE model with known load and material properties. It was found that in the case of significant deflections, the linear Kirchoff model was not accurate. The non-linear Föppl--von Kàrmàn model takes into account the occurring membrane stresses and extends on the Kirchhoff model, allowing for larger deflection. The non-linear Föppl--von Kàrmàn model was found to successfully describe the simulated situation and could be used to better solve for the paperboard's bending stiffness values over two axes.

Tensor‐based process control and monitoring for semiconductor manufacturing with unstable disturbances

Tensor‐based process control and monitoring for semiconductor manufacturing with unstable disturbances

Reliability inference of a multicomponent stress-strength model for exponentiated Pareto distribution based on progressive first failure censored samples

Multicomponent stress-strength (MC-SS) analysis is crucial for risk management and decision-making in various fields such as engineering, manufacturing, and quality control. It helps in identifying vulnerable components and areas where improvements can enhance overall system reliability. A primary contribution of this research is the implementation of the progressive first-Failure censored (PFIF-C) scheme. This scheme offers a novel and efficient approach to time and cost censoring, surpassing many existing censoring schemes found in the literature. The current study investigates the issue of MC-SS reliability inference under PFIF-C from the exponentiated Pareto distribution. The reliability of the MC-SS system is considered under the condition that both stress and strength follow an exponentiated Pareto distribution with a common second shape parameter. The parameter estimates and reliability estimate of the MC-SS system is produced using the maximum likelihood and Bayesian procedures. The asymptotic confidence intervals and highest posterior density credible intervals for the MC-SS system reliability are produced. Bayesian estimates are yielded using Markov Chain Monte Carlo under both informative and non-informative priors, considering symmetric and asymmetric loss functions. In order to assess the efficacy of the suggested methodology, simulation analyses are conducted. According to the simulation data Bayesian estimates of the MC-SS reliability, employing both symmetric and asymmetric loss functions, consistently outperform maximum likelihood estimates in terms of estimated risks. In general, Bayesian estimates based on asymmetric loss function perform better than the other competing loss function. The procedure is further shown with one real-world data example about failure times of a specific software model to show how the recommended approach may be applied to assess the strength and stress of a multicomponent model.

Heavy Metals and Cosmetics Industry: A Review Article

Trace amounts of heavy metals are present during cosmetic products manufacturing. (1) Therefore, they should be kept to a minimum acceptable level as stated by the FDA and pharmacopeias. (2) It is so far known that human external contact with these substances rarely result in a significant systemic exposure. However, many research studies showed that frequent local exposure to cosmetic products containing heavy metals may pose a risk of heavy metal contamination. (1,2) Heavy metals such as mercury (Hg) are added to skin-whitening products, causing acute or chronic damage to human skin cells. (1) Moreover, contamination of hair dyes and deodorants with Aluminum (Al) and Lead (Pb) threaten consumers' health dangerously for carcinogenic effects. Other possible side effects included microcytic anemia and osteomalacia. (3) Additionally, it was found that Al provokes further side effects on human mental health as dialysis dementia and it has also been associated with the neurodegenerative disease, Alzheimer's disease (AD) in adults. (4) Furthermore, Pb is a core component of many lipsticks, which reflects a high systemic absorption due to wrong consumers' habits. Frequent use of lipsticks containing Pb specially by children and adolescents has been significantly linked to neurodevelopmental disorders such as autism and attention-deficit-hyperactivity-disorder (ADHD) symptoms in children. (5) Therefore, strict regulations should be set for cosmetics manufacturing and quality control measurements should be assigned for pre- and post-marketed cosmetic products.

Double kernel and minimum variance embedded broad learning system based autoencoder for one-class classification

One-class classification methods are often used for anomaly detection in healthcare, quality control in manufacturing, and fraud detection in financial services. Particularly in medical datasets, instances of rare cancers are considerably fewer in comparison to those of healthy individuals. One-class classification methods, which concentrate on learning models using just samples from a specified class, have drawn increasing attention as a solution to this problem. To enhance the model’s ability to capture essential feature information, we propose a novel strategy in this paper. This strategy involves the initial application of double kernel mapping, translating the original features into a new feature space. The autoencoder based on the Broad Learning System is then modified to incorporate the minimum variance so that the model can learn the potential feature information. We validated the effectiveness of our proposed strategy using UCI dataset and concordia digits dataset. To compare the performance with other one-class methods, the average F1 scores and the average G−mean are employed as comparative measures. Based on experimental results, it is evident that DKVBLS-AE not only outperforms but also demonstrates greater stability compared to the existing methods.

Exploring the Frontiers: A Comprehensive Review of Augmented Reality and Virtual Reality in Manufacturing and Industry

Augmented reality (AR) and virtual reality (VR) are revo- lutionizing manufacturing practices by offering immersive and interactive experiences. This review paper synthesizes current research on AR and VR’s applications, benefits, and challenges in manufacturing, covering design, training, maintenance, and quality control. Key findings highlight the applications and positive impact of AR/VR on efficiency, cost management, and quality control in manufacturing processes. Industries are in- creasingly adopting these technologies to enhance productivity and reduce errors. However, challenges such as cost, techno- logical infrastructure, and integration into existing workflows remain significant barriers. In conclusion, integrating AR and VR in manufacturing holds immense potential to transform traditional methods and improve operational efficiency. This paper advocates for broader implementation and research to harness the full benefits of immersive technologies in manufacturing.

Regulatory cell therapy for kidney transplantation and autoimmune kidney diseases.

Regulatory cell therapies, including regulatory T cells and mesenchymal stromal cells, have shown promise in early clinical trials for reducing immunosuppression burden in transplantation. While regulatory cell therapies may also offer potential for treating autoimmune kidney diseases, data remains sparse, limited mainly to preclinical studies. This review synthesises current literature on the application of regulatory cell therapies in these fields, highlighting the safety and efficacy shown in existing clinical trials. We discuss the need for further clinical validation, optimisation of clinical and immune monitoring protocols, and the challenges of manufacturing and quality control under Good Manufacturing Practice conditions, particularly for investigator-led trials. Additionally, we explore the potential for expanding clinical indications and the unique challenges posed in paediatric applications. Future directions include scaling up production, refining protocols to ensure consistent quality across manufacturing sites, and extending applications to other immune-mediated diseases.

In situ Synchrotron X-ray Metrology Boosted by Automated Data Analysis for Real-time Monitoring of Cathode Calcination.

Synchrotron X-ray-based in situ metrology is advantageous for monitoring the synthesis of battery materials, offering high throughput, high spatial and temporal resolution, and chemical sensitivity. However, the rapid generation of massive data poses a challenge to on-site, on-the-fly analysis needed for real-time process monitoring. Here, a weighted lagged cross-correlation (WLCC) similarity approach is presented for automated data analysis, which merges with in situ synchrotron X-ray diffraction metrology to monitor the calcination process of the archetypal nickel-based cathode, LiNiO2. The WLCC approach, incorporating variables that account for peak shifts and width changes associated with structural transformations, enables rapid extraction of phase progression within 10 seconds from tens of diffraction patterns. Details are captured, from initial precursors to intermediates and the final layered LiNiO2, providing information for agile on-site adjustments during experiments and complementing post hoc diffraction analysis by offering insights into early-stage phase nucleation and growth. Expanding this data-powered platform paves the way for real time calcination process monitoring and control, which is pivotal to quality control in battery cathode manufacturing.