Complex Production Processes Research Articles

Semiconductor Wafer Defect Detection Based on Machine Learning

Semiconductor wafers are widely used in integrated circuit chips. Because of the complex production process, it is easy to cause various defects. Therefore, the defect detection of semiconductor wafers is an important means to ensure their yield and productivity. This paper mainly expounds on the detection method of wafer defects combined with the machine vision algorithm, including the CNN model, and the classification of the learning-based methods. Current problems and future prospects for total crystalline circle defect detection are discussed in the end.

In situ engineering of mRNA-CAR T cells using spleen-targeted ionizable lipid nanoparticles to eliminate cancer cells

Chimeric antigen receptor (CAR) T cell therapy has implemented impressive advances in the treatment of B-cell lymphoma. However, the complex production process of CAR T cells and hindrance of solid tumor penetration remain substantial challenges. Intriguingly, cell-targeting delivery of messenger RNA (mRNA) with ionizable lipid nanoparticles (mRNA-LNPs) is able to efficiently and precisely engineer T cells and other immune cells in vivo to perform their functions. Herein, we harnessed the ionizable LNPs to encapsulate mRNA encoding anti-tyrosinase related protein 1 (TRP1) CAR (CAR-LNPs) for in vivo generation of mRNA-CAR T cells to eliminate melanoma cells. Specifically, the anti-CD3 antibody (aCD3) armed mRNA-LNPs (CD3-mRNA-LNPs) selectively targeted T cells, resulting in the production of functional and therapeutic levels of CAR T cells both ex vivo and in vivo. These CD3-CAR-LNPs engineered CAR T cells were capable of infiltrating into the solid tumor and effectively eliminating melanoma cells with high TRP1 expression, significantly hindering tumor progression. Critically, CD3–7CAR-LNPs containing mRNA encoding both CAR and interleukin-7 (IL-7) generated 7CAR T cells that secreted IL-7, thereby enhancing the activity and proliferation of both CAR T cells and other intratumoral cytotoxic T cells. Alternatively, the employment of anti-programmed cell death protein 1 antibody (aPD-1) protected mRNA-CAR T cells from exhaustion, especially in combination with CD3–7CAR-LNPs, could significantly enhance the antitumor capability of CAR T cells without causing acute cytokine release syndrome (CRS).

Fe0-MAP Prepared Glycosurfaces for Selective Cell Capture: From Adherent to Suspended Cells.

The specific capture of live cells is crucial for various biomedical applications. Existing methods often are limited by complex production processes. This study introduces Fe0-mediated monomer-adaptation polymerization (Fe0-MAP), a convenient and rapid synthesis approach for selective cell capture using surface-engineered glycopolymer brushes. This method utilizes surface-initiated zerovalent iron-mediated reversible-deactivation radical polymerization (Fe0-SI-RDRP), offering advantages like simplicity, biocompatibility and oxygen-tolerance due to the use of iron sheet as catalysts. We successfully employed Fe0-MAP to selective capture both adherent (HeLa, L929) and suspended cells (Ramos, U937) in mammalian cell cultures. Combining excellent biocompatibility, specific and reusable cell capture capabilities, and applicability to suspended cells, Fe0-MAP establishes itself as a promising strategy for selective cell capture, holding significant potential for diverse biomedical applications.

The Influence of Safety Leadership and Safety Climate on Safety Behavior is Mediated by Safety Motivation in Sugar Factory Employees

The sugar industry has complex production processes and involves various risks, including the high potential for employee accidents. To reduce this risk, the implementation of an effective work safety programme is required. This reserach aims to analyse the effect of safety leadership and safety climate on safety behaviour mediated by safety motivation in sugar factory employees. The method used is quantitative with data collection through questionnaires. The population of this study were all sugar factory employees in Indonesia, with a sample of 100 respondents selected using random sampling technique. Data analysis was carried out using Path Analysis in the SEM-PLS programme. The results showed that Safety Leadership and Safety Climate positively influence the Safety Behaviour of sugar factory employees. In addition, Safety Motivation mediates the influence of Safety Leadership and Safety Climate on Safety Behaviour, which indicates that Safety Motivation can strengthen the influence of these two factors on the safety behaviour of sugar factory employees. This reserach provides important implications for sugar factory management to pay more attention to aspects of motivation and safety climate to improve safety behaviour in the workplace.

PERANCANGAN APLIKASI MANAJEMEN PRODUKSI KOPI PT. KARYA BAKTI BERBASIS WEB DENGAN MENGGUNAKAN MODEL PROTOTYPE

The coffee industry has a complex production process right up to the distribution of the final product. Along with increasing competition in the coffee industry, PT. Karya Bakti faces the challenge of increasing productivity, maintaining product quality, and optimizing the supply chain. To manage this process efficiently and effectively, PT. Karya Bakti requires a management system that is reliable and can be accessed easily. Thus, this research will discuss how to design and build an information system and find out how to implement coffee production management applications at PT. Web-based Bakti Work. In this research, the UML method is used as a means of designing an object-oriented system with a Prototype model. In this research, to find out the problems that occur in a system, it is a good idea to analyze the operating system and try to understand how the system works well. After that, the proposed system design is carried out, there will be an admin who will have full control over the system by creating use cases, class diagrams, activity diagrams. In the design of a web-based coffee production management application, the users who can use this application are the authorized departments in production management. In accordance with the system design previously discovered, the application has several list display designs for the data displayed on the application pages. This research produces a management information system to help PT. Karya Bakti in processing data, both sales data, income data, roasting data, purchase or order data. With this information system, it has made it easier for PT. Karya Bakti in making monthly or annual reports with a success rate of 70%, coffee production management information system PT. Karya Bakti can increase efficiency and productivity and this coffee production management information system was only developed specifically for PT. Community Service. However, the author hopes that this system will be developed in a mobile version and because this information system is not yet equipped with employee management, recitation and inventory features, it is highly recommended for future research to add these features. Keywords: Design, Application, Management, Web, Prototype

Smart calibration and monitoring: leveraging artificial intelligence to improve MEMS-based inertial sensor calibration

Micro-electro-mechanical systems (MEMS)-based sensors endure complex production processes that inherently include high variance. To meet rigorous client demands (such as sensitivity, offset noise, robustness against vibration, etc.). products must go through comprehensive calibration and testing procedures. All sensors undergo a standardized and sequential calibration process with a predetermined number of steps, even though some may reach the correct calibration value sooner. Moreover, the traditional sequential calibration method faces challenges due to specific operating conditions resulting from manufacturing discrepancies. This not only extends the calibration duration but also introduces rigidity and inefficiency. To tackle the issue of production variances and elongated calibration time and enhance efficiency, we provide a novel quasi-parallelized calibration framework aided by an artificial intelligence (AI) based solution. Our suggested method utilizes a supervised tree-based regression technique and statistical measures to dynamically identify and optimize the appropriate working point for each sensor. The objective is to decrease the total calibration duration while ensuring accuracy. The findings of our investigation show a time reduction of 23.8% for calibration, leading to substantial cost savings in the manufacturing process. In addition, we propose an end-to-end monitoring system to accelerate the incorporation of our framework into production. This not only guarantees the prompt execution of our solution but also enables the identification of process modifications or data irregularities, promoting a more agile and adaptable production process.

A FRAMEWORK FOR LEAN MANUFACTURING IMPLEMENTATION IN THE TEXTILE INDUSTRY: A RESEARCH STUDY

This study investigates the implementation of lean manufacturing in the textile industry, focusing on its potential to enhance efficiency, reduce waste, and improve product quality. Lean manufacturing principles, including Just-In-Time (JIT) production, Kanban systems, value stream mapping, 5S workplace organization, and continuous improvement (Kaizen), have been widely recognized for their effectiveness in various manufacturing sectors. However, their application in the textile industry remains underexplored. Through a systematic literature review of 60 review papers and empirical analysis involving case studies, interviews, and surveys with industry experts, managers, and workers, this research identifies the significant benefits of lean practices in textile manufacturing. The findings reveal substantial efficiency gains, waste reduction, and quality improvements among companies adopting lean principles. Nevertheless, the study also highlights several industry-specific challenges, such as high variability in raw materials, complex production processes, and market pressures from fast fashion. These challenges necessitate tailored approaches and effective change management strategies for successful lean integration. Additionally, the research emphasizes the need for investment in advanced technologies and flexible manufacturing systems to enhance responsiveness to market changes. The study concludes that despite the challenges, lean manufacturing offers valuable strategies for textile companies aiming to improve their competitiveness and sustainability in the global market. This research contributes to the growing body of knowledge on lean manufacturing and provides practical insights for textile manufacturers seeking to adopt and optimize lean practices.

Lean-and-Green Fractional Factorial Screening of 3D-Printed ABS Mechanical Properties Using a Gibbs Sampler and a Neutrosophic Profiler

The use of acrylonitrile butadiene styrene (ABS) in additive manufacturing applications constitutes an elucidating example of a promising match of a sustainable material to a sustainable production process. Lean-and-green datacentric-based techniques may enhance the sustainability of product-making and process-improvement efforts. The mechanical properties—the yield strength and the ultimate compression strength—of 3D-printed ABS product specimens are profiled by considering as many as eleven controlling factors at the process/product design stage. A fractional-factorial trial planner is used to sustainably suppress by three orders of magnitude the experimental needs for materials, machine time, and work hours. A Gibbs sampler and a neutrosophic profiler are employed to treat the complex production process by taking into account potential data uncertainty complications due to multiple distributions and indeterminacy issues due to inconsistencies owing to mechanical testing conditions. The small-data multifactorial screening outcomes appeared to steadily converge to three factors (the layer height, the infill pattern angle, and the outline overlap) with a couple of extra factors (the number of top/bottom layers and the infill density) to supplement the linear modeling effort and provide adequate predictions for maximizing the responses of the two examined mechanical properties. The performance of the optimal 3D-printed ABS specimens exhibited sustainably acceptable discrepancies, which were estimated at 3.5% for the confirmed mean yield strength of 51.70 MPa and at 5.5% for the confirmed mean ultimate compression strength of 53.58 MPa. The verified predictors that were optimally determined from this study were (1) the layer thickness—set at 0.1 mm; (2) the infill angle—set at 0°; (3) the outline overlap—set at 80%; (4) the number of top/bottom layers—set at 5; and (5) the infill density—set at 100%. The multifactorial datacentric approach composed of a fractional-factorial trial planner, a Gibbs sampler, and a neutrosophic profiler may be further tested on more intricate materials and composites while introducing additional product/process characteristics.

Characterization the microbial diversity and functional genes in the multi-component contaminated groundwater in a petrochemical site.

Microorganisms in groundwater at petroleum hydrocarbon (PHC)-contaminated sites are crucial for PHC natural attenuation. Studies mainly focused on the microbial communities and functions in groundwater contaminated by PHC only. However, due to diverse raw and auxiliary materials and the complex production processes, in some petrochemical sites, groundwater suffered multi-component contamination, but the microbial structure remains unclear. To solve the problem, in the study, a petrochemical enterprise site, where the groundwater suffered multi-component pollution by PHC and sulfates, was selected. Using hydrochemistry, 16S rRNA gene, and metagenomic sequencing analyses, the relationships among electron acceptors, microbial diversity, functional genes, and their interactions were investigated. Results showed that different production processes led to different microbial structures. Overall, pollution reduced species richness but increased the abundance of specific species. The multi-component contamination multiplied a considerable number of hydrocarbon-degrading and sulfate-reducing microorganisms, and the introduced sulfates might have promoted the biodegradation of PHC. PRACTITIONER POINTS: The compound pollution of the site changed the microbial community structure. Sulfate can promote the degradation of petroleum hydrocarbons by hydrocarbon-degrading microorganisms. The combined contamination of petroleum hydrocarbons and sulfates will decrease the species richness but increase the abundance of endemic species.

Industrial automation and product quality: the role of robotic production transformation

ABSTRACT We investigate the impact of industrial automation, specifically robots, on product quality in international trade. By analysing detailed data from Chinese listed firms, we examine how the adoption of robots is associated with higher product quality compared to that of nonrobot users. This effect is more pronounced among heterogeneous products and in ordinary trade patterns. We identify several mechanisms through which robots contribute to product quality improvements, including resource reallocation, adaptability to complex production processes, and enhancement of input quality. Moreover, we demonstrate that replacing low-skilled labour with complex robots and employing high-skilled labour to collaborate with robots improved product quality, confirming that robotic displacement and reinstatement effects generate better product quality upgrading. Overall, our empirical evidence supports the positive influence of robot adoption on product quality and provides insights into the mechanisms underlying robotic production transformation.

Integrating geospatial data and street‐view imagery to reconstruct large‐scale 3D urban building models

Abstract3D urban building modeling is a vital foundational step for building Digital Twins and Smart Cities. In response to existing challenges, such as high time costs, complex production processes, and low consistency with real‐world textures in large‐scale 3D urban building modeling methods, this research proposes a reconstructing 3D urban building models (3DUBM) approach that integrates geospatial data and street view. The approach achieves an enhanced generation of large‐scale 3DUBMs. Based on open geospatial data and street‐view imagery (SVI), the approach was tested in modeling experiments conducted in Shanghai, Hongkong, and Nanjing. Furthermore, a dataset covering unique blocks of 30 cities in China was constructed to demonstrate the approach's characteristics of large coverage, high time efficiency, high model quality and low economic cost. The accuracy of texture mapping from SVI to 3DUBM reached 85%. This achievement has significant economic value in bridging the gap in the production of large‐scale and low‐cost 3DUBM data, promoting the construction of Digital Twins, Smart Cities, and Real‐world 3D modeling.

Exploring the Impact of Various Wooden Barrels on the Aromatic Profile of Aceto Balsamico Tradizionale di Modena by Means of Principal Component Analysis.

The study examines the unique production process of Aceto Balsamico Tradizionale di Modena PDO (ABTM), emphasizing its complex phases and the impact of raw materials and artisanal skill on its flavor characteristics. Analytical tests focused on the volatile composition of vinegars from different wood barrels at different aging stages, using solid-phase micro-extraction (SPME) coupled with gas chromatography, either with mass spectrometry (GC/MS) or flame ionization detector (FID). Multivariate analysis, including principal component analysis (PCA), was employed to investigate the presence of peculiarities among the volatile profiles of samples of different barrel origin. The research focuses on characterizing the volatile composition of vinegars sourced from individual wood barrels, such as Cherry, Chestnut, Mulberry, Juniper, and Oak. Although it was not possible to identify molecules directly connected to the woody essence, some similarities emerged between vinegar samples from mulberry and cherry barrels and between those of juniper and oak. The former group is characterized by analytes with high molecular weights, such as furfural and esters, while the latter group shows more intense peaks for ethyl benzoate. Moreover, ethyl benzoate appears to predominantly influence samples from chestnut barrels. Due to the highly complex production process of ABTM, where each battery is influenced by several factors, this study's findings are specific to the current experimental conditions.

Recent Patents for Machine Vision Inspection in the Machine Tool Sector

Abstract:: In the current modern manufacturing industry, the demand for product quality control is increasing, as is the need for automation. However, the manual inspection may need to be noticed or undetectable in the complex production process. To solve this phenomenon, machine vision-based inspection of machine tools and their product features has become one of the key technologies in intelligent manufacturing. The basic principle of machine tool machine vision inspection is to transmit the object to be inspected to the computer through efficient image acquisition. Then, image processing or deep learning algorithms classify, locate, segment, and process the features of the thing. Finally, the computer makes the judgment of whether it is qualified. According to recent numerical analysis data, compared with traditional methods, machine tool machine vision inspection can improve the inspection efficiency by 30%, and the accuracy has reached 98%, much higher than manual inspection accuracy. This study provides an in-depth review of representative patents and machine tool vision inspectionpatents , and it comprehensively summarizes the research results from various dimensions in recent year. In the past five years, the average annual growth rate of machine tool vision inspection technology has reached 15%, showing the rapid development momentum of this field. The research content mainly focuses on designing vision detection structures, algorithm optimization designs, and personalized solutions for object differences.

Preliminary Purification and Partial Characterization of a Functional Bacteriocin of Lacticaseibacillus paracasei Zhang and Mining for its Gene Cluster.

Bacteriocins produced by lactic acid bacteria (LAB) have good potential for use as food biopreservatives. Lacticaseibacillus paracasei Zhang (L. paracasei Zhang) is both a food use and a probiotic bacterium. This study aimed to purify and preliminary characterize the active antibacterial metabolite of L. paracasei Zhang. The cell-free supernatant of L. paracasei Zhang was collected and purified by ultrafiltration and gel filtration chromatography. The 1-3kDa active fraction could inhibit the growth of Staphylococcus aureus but not Escherichia coli. Further antibacterial activity assays revealed its capacity to suppress various foodborne and human opportunistic pathogens (including Staphylococcus aureus, Pseudomonas fluorescens, Pseudomonas aeruginosa, Listeria monocytogenes, and Bacillus cereus), but not fungi. The antibacterial activity showed good tolerance to heat (40 to 100°C), acid-base (pH 2-3 and pH 6-10), and digestions by a number of industrial and animal/human enzymes (such as trypsin, pepsin, α-amylase, and protease K, except papain); these desired properties make it a suitable biopreservative to be used in harsh and complex industrial production processes. The high papain sensitivity suggested a proteinaceous/peptide nature of the bioactivity. Moreover, our genomic data mining for bacteriocin through BAGEL4 revealed an area of interest encoding a complete set of putative genes required for bacteriocin production. In conclusion, our study showed that L. paracasei Zhang can produce extracellular functional antibacterial metabolite, likely a class II bacteriocin. Our preliminary extraction and characterization of the active metabolite demonstrated that it has good potential to be used as a biopreservative or an agent for suppressing gastrointestinal infections.

Concept Paper for a Digital Expert: Systematic Derivation of (Causal) Bayesian Networks Based on Ontologies for Knowledge-Based Production Steps

Despite increasing digitalization and automation, complex production processes often require human judgment/decision-making adaptability. Humans can abstract and transfer knowledge to new situations. People in production are an irreplaceable resource. This paper presents a new concept for digitizing human expertise and their ability to make knowledge-based decisions in the production area based on ontologies and causal Bayesian networks for further research. Dedicated approaches for the ontology-based creation of Bayesian networks exist in the literature. Therefore, we first comprehensively analyze previous studies and summarize the approaches. We then add the causal perspective, which has often not been an explicit subject of consideration. We see a research gap in the systematic and structured approach to ontology-based generation of causal graphs (CGs). At the current state of knowledge, the semantic understanding of a domain formalized in an ontology can contribute to developing a generic approach to derive a CG. The ontology functions as a knowledge base by formally representing knowledge and experience. Causal inference calculations can mathematically imitate the human decision-making process under uncertainty. Therefore, a systematic ontology-based approach to building a CG can allow digitizing the human ability to make decisions based on experience and knowledge.

Self-Supervised Learning and Multisource Heterogeneous Information Fusion Based Quality Anomaly Detection for Heavy-Plate Shape

Plate shape quality anomaly detection suffers from the problems of less labeled and multisource heterogeneous (MSH) data due to the complex production process with multi-process and multi-equipment. To address these problems, this paper proposes a self-supervised learning framework based on MSH contrastive learning (MSH-CL). In the proposed framework, an encoder is designed to extract the MSH information, which contains an MSH feature extract network (MSH-FEN) and an MSH feature fusion network (MSH-FFN). In MSH-FEN, a two-pathway CNN network is employed to extract the MSH feature. Then, a cross-MSH (CMSH) data fusion strategy based on the attention mechanism is designed to characterize the relationship between the MSH data in the MSH-FFN. The learning process consists of two phases, namely the self-supervised feature learning phase based on the contrastive learning (CL) and the supervised fine-tuning phase. The former phase is responsible for training the encoder with massive unlabeled data. Then, a classifier followed by the encoder is built with less labeled data in the supervised fine-tuning phase, which is applied to plate shape quality anomaly detection. Finally, the experiments are carried out on the real-world data set collected from a heavy-plate production process. The experimental results demonstrate the effectiveness and superiority of the proposed approach. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper focuses on the problem of shape quality anomaly detection for the heavy-plate production process, which is crucial to steel-making. However, the most quality-relevant data-driven modeling approaches suffer from the problem of requiring massive labeled data. In addition, the data generated in the practice heavy-plate production process have the characteristics of multisource heterogeneous (MSH). Motivated by the challenge of the less labeled and MSH data modeling, this paper proposed a self-supervised feature learning approach to learn a feature encoder to model the MSH data. Then, fine-tuning is used to obtain the model to detect the plate shape quality. In the feature encoder, a cross-MSH (CMSH) data fusion strategy is proposed. Finally, the effectiveness of the proposed approach is demonstrated by comparing it with other advanced algorithms. The proposed approach can be extended to other heavy-plate quality anomaly detection problems with less labeled and MSH data.

Application of Arc Furnace Flue Ash in Casting Heat Insulation Riser

Iron black commonly employs in thermal insulation riser sleeves due to its ability to react with aluminum powder, generating heat. However, the complex production process and unstable composition of iron black lead to high production costs. The potential of using arc furnace flue ash (AFFA) as a complete substitute for iron black and MnO2 and KNO3 oxidizing agents in conventional riser sleeves was investigated in this study. Waste material can be transformed into a valuable resource, while production costs can be reduced by utilizing arc furnace flue ash. The research examined the impact of varying types and amounts of arc furnace flue ash on riser sleeve temperature and holding time by conducting single-factor and orthogonal optimization experiments. The orthogonal optimization experiment determined that the optimum ratio of each oxidant was 6 % arc flue ash, 3 % MnO2 and 6 % KNO3. At this time, the highest temperature was 1512 ℃ and the holding time was 244 s. Results indicated that different types of arc furnace flue ash used as an oxidizing agent demonstrated superior holding capacity and heat generation performance compared to iron black. Additionally, a comparative analysis of factory casting experiments using ductile iron 600-3 (IS) revealed that both arc furnace flue ash and iron black risers effectively countered shrinkage. However, arc furnace flue ash risers exhibited improved mechanical properties, as evidenced by the hardness of the castings.

Evolutionary modeling approach based on multiobjective genetic programming for strip quality prediction

In the iron and steel industry, hardness is one of the key indicators of strip quality in the continuous annealing production line (CAPL). However, the complex production process and the strong coupled nonlinearity between process parameters make it difficult to develop accurate mechanism models and pose a challenge for data-driven modeling approaches. More importantly, most of the data-driven learning methods lack interpretability and cannot characterize the mathematical relationship between process parameters and product quality, which in turn makes it extremely hard to understand the process mechanism. Therefore, this paper proposes an interpretable modeling approach (IMA) based on feature decomposition and ensemble to construct interpretable analytical models between process parameters and strip quality. In the IMA, a data-mechanism fusion-based feature decomposition (DM_FD) method is first applied to cope with high-dimensional input feature problems. Then, an improved multiobjective genetic programming algorithm (iMOGP) is developed to construct interpretability sub-models. Finally, a sparse optimization ensemble method (SOE) is used to integrate the sub-models to achieve interpretability and good generalization. Experimental results based on practical strip data demonstrate that the proposed IMA can cope well with high-dimensional input features and achieve model interpretability compared with commonly used machine learning methods and genetic programming (GP)-based modeling methods while ensuring better accuracy and generalization.

A process knowledge-based hybrid method for univariate time series prediction with uncertain inputs in process industry

In process industry, accurate and efficient univariate time series prediction (TSP) of key process parameters is crucial for optimizing production processes. However, noisy data and varying working conditions introduce uncertainties that hinder the modeling process. Data-driven methods have been proposed to address input-uncertain TSP models, but they often fail to obtain sufficient and high-quality industrial data for model establishment in complex and dynamic production process. The paper presents a process knowledge-based hybrid method for univariate TSP that handles noisy inputs in different working conditions. Primarily, a knowledge-embedded deep kernel network (KE-DKN) model is proposed that approximates the outputs to the knowledge space in noisy industrial environment, by embedding instantiated process knowledge as soft constraints into the conventional DKN network. Further, a two-stage training schema is designed for KE-DKN to reduce the interference superposition on the predicted variable from random noisy data and operational interferences. Moreover, the pre-trained parameters transferring is conducted from stable working conditions to mitigate the low modeling efficiency in unstable working conditions. In two cases from process industry, the proposed method delivers higher prediction accuracy and robustness than baseline methods in both working conditions, and the knowledge transfer significantly enhances the modeling efficiency in unstable working conditions.

Requirements engineering in industry 4.0: State of the art and directions to continuous requirements engineering

AbstractThe 4th Industrial Revolution, also known as Industry 4.0, intends to transform manufacturing processes into smart factories with full digitalization and intelligent, decentralized, and flexible production. In this scenario, Industry 4.0 systems (i.e., software‐intensive systems that automate smart factories) have required rigorous and continuous development, but smart factory companies often have difficulty dealing with Requirements Engineering (RE) where requirements continuously change and emerge at runtime to support the changeability of complex production processes. Such requirements encompass engineering (e.g., mechanical, electrical, electronic, production/manufacturing) and business areas and involve the vertical and horizontal integration of heterogeneous manufacturing systems. There is also a lack of a panorama of how Industry 4.0 projects have performed with RE activities. The main goal of this paper is to present the state‐of‐the‐art research concerning RE in Industry 4.0 and draw attention to the next most urgent steps. For this, we selected and examined studies that address RE for Industry 4.0, noting that much of this literature is recent but does not fully address the complexity and dynamism of the requirements for Industry 4.0. Grounded on these studies and our academic and industry experience, we highlight the need for Continuous Requirements Engineering (CRE) for Industry 4.0.Significance and Practitioner Points: The main implications of this paper are: (i) For researchers: It offers the state of the art of RE in the context of Industry 4.0 and points out several important open issues that require an urgent investigation through new research topics; and (ii) For practitioners: It provides directions for new or even existing Industry 4.0 projects on how to deal with RE activities aiming to overcome the several challenges to perform them.