Search

Modern manufacturing has to cope with dynamic and changing circumstances. Market fluctuations, the effects caused by unpredictable material shortages, highly variable product demand, and worker availability all require system robustness, flexibility, and resilience. To adapt to these new requirements, manufacturers should consider investigating, investing in, and implementing system autonomy. Autonomy is being adopted in multiple industrial contexts, but divergences arise when formalizing the concept of autonomous systems. To develop an implementation of autonomous manufacturing systems, it is essential to specify what autonomy means, how autonomous manufacturing systems are different from other autonomous systems, and how autonomous manufacturing systems are identified and achieved through the main features and enabling technologies. With a comprehensive literature review, this paper provides a definition of autonomy in the manufacturing context, infers the features of autonomy from different engineering domains, and presents a five-level model of autonomy — associated with maturity levels for the features — to ensure the complete identification and evaluation of autonomous manufacturing systems. The paper also presents the evaluation of a real autonomous system that serves as a use-case and a validation of the model. [ABSTRACT FROM AUTHOR]

Machine learning methods have shown potential for the optimization of production processes. Due to the complex relationships often inherent in those processes, the success of such methods is often uncertain and unreliable. Therefore, understanding the (algorithmic) behavior and results of machine learning methods is crucial to improve the prediction of production processes. Here, mathematical tools may help. This paper shows how efficient algorithms for the training of neural networks and their retraining in the framework of transfer learning are expressed in a discrete as well as a time-continuous formulation. The latter can be analyzed and investigated using mathematical techniques from kinetic gas dynamics. The results obtained provide a first step towards explainable artificial intelligence. Based on the mathematical description, an adapted ensemble method for retraining of neural networks is proposed and compared with backpropagation algorithms. The process of training and retraining is a common task and therefore demonstrated for two very different production processes. The first one involves the prediction of specific cutting forces and the second one the prediction of particle properties in a plasma spraying coating process. For both use cases, the presented algorithms are applied and their performance is evaluated giving thereby an indication how mathematically inspired methods improve classical tasks in production processes. [ABSTRACT FROM AUTHOR]

Engineering and manufacturing processes and systems designs involve many challenges, such as dynamism, chaotic behaviours, and complexity. Of late, the arrival of big data, high computational speed, cloud computing and artificial intelligence techniques (like machine learning and deep learning) has reformed how many engineering and manufacturing professionals approach their work. These technologies offer thrilling innovative ways for engineers and manufacturers to tackle real-life challenges. On the other hand, the field of Artificial Intelligence (AI) is extensive. Several diverse theories, algorithms, and methods are available, which presents a challenge and a barrier in choosing the right AI technique for the appropriate engineering process or manufacturing process and environments. Besides, the pertinent literature is disseminated over various journals, conference proceedings, and research communities. Hence, conducting a systematic survey to scrutinise and classify the existing literature is worthwhile. However, it is challenging, but previous review studies have not adequately addressed AI's use and advancement in engineering and manufacturing (EM). Besides, some concentrated on single AI models, and others focused on a specific area in EM. This paper presents a comprehensive systematic review of studies on AI and its application in EM. To limit the scope of the current study, we conducted a keyword search in official publisher websites and academic databases, such as Springer, Elsevier, Scopus, Science Publication, Taylor & Francis, Directory of Open Access Journals (DOAJ), Association for Computing Machinery (ACM), Wiley online library, Inderscience and Google scholar. The search results (173 articles) were filtered according to a proposed framework, which resulted in ninety-one (91) relevant research articles. We reviewed the articles based on a proposed taxonomy (the year of publication, the AI algorithm and machine learning task adopted, the application area in EM, the train and test split of data, the error, and accuracy metrics used, the potential benefits). Our assessment using the proposed taxonomy gave a helpful insight into the literature's anatomy on various AI applications in engineering and manufacturing. Also, we identified opportunities for future research in AI application in the field of EM. [ABSTRACT FROM AUTHOR]

Modern cutting tools like end mills, drilling tools, and reamers underlie high requirements regarding geometrical accuracy, cutting edge quality, and production costs. However, the potential for process optimization is limited due to the process kinematics during grinding. Consequently, a novel tool grinding process for the manufacture of cutting tools has been developed recently at the Institute for Production Engineering and Machine Tools (IFW). This continuous generating grinding process allows the simultaneous production of all flutes and circumferential flank faces of rotational symmetrical cutting tools. The present paper focuses on the geometrical process design and develops a method to determine the necessary basic rack and process parameters in order to create a desired cutting edge geometry by continuous generating grinding. The developed method can define all parameters with an accuracy of up to 5 µm and 0.2° within a simulation in five iteration steps and allows not only the quantitative design of the cutting tool geometry but a qualitative modification of the flute geometry as well. Subsequently performed grinding tests showed that the presented method allows the design of grinding worms for continuous generating grinding of cutting tools and enables the successful implementation of these processes. [ABSTRACT FROM AUTHOR]

Advanced analytics are fundamental to transform large manufacturing data into resourceful knowledge for various purposes. In its very nature, such "industrial big data" can relay its usefulness to reach further utilitarian applications. In this context, Machine Learning (ML) is among the major predictive modeling approaches that can enable manufacturing researchers and practitioners to improve the product quality and achieve resource efficiency by exploiting large amounts of data (which is collected during manufacturing process). However, disposing ML algorithms is a challenging task for manufacturing industrial actors due to the prior specification of one or more algorithms hyperparameters (HPs) and their values. Moreover, manufacturing industrial actors often lack the technical expertise to apply advanced analytics. Consequently, it necessitates frequent consultations with data scientists; but such collaborations tends to cost the delays, which can generate the risks such as human-resource bottlenecks. As the complexity of these tasks increases, so does the demand for support solutions. In response, the field of automated ML (AutoML) is a data mining-based formalism that aims to reduce human effort and speedup the development cycle through automation. In this regard, existing approaches include evolutionary algorithms, Bayesian optimization, and reinforcement learning. These approaches mainly focus on providing the user assistance by automating the partial or entire data analysis process, but they provide very limited details concerning their impact on the analysis. The major goal of these conventional approaches has been generally focused on the performance factors, while the other important and even crucial aspects such as computational complexity are rather omitted. Therefore, in this paper, we present a novel meta-learning based approach to automate ML predictive models built over the industrial big data. The approach is leveraged with development of, AMLBID, an Automated ML tool for Big Industrial Data analyses. It attempts to support the manufacturing engineers and researchers who presumably have meager skills to carry out the advanced analytics. The empirical results show that AMLBID surpasses the state-of-the-art approaches and could retrieve the usefulness of large manufacturing data to prosper the research in manufacturing domain and improve the use of predictive models instead of precluding their outcomes. [ABSTRACT FROM AUTHOR]

In this study, we examine innovative design practices on the Saint-Nazaire Airbus factory shop floor. The engineering and manufacturing engineering departments are in charge of the design of products and their industrialization, even though the factory is usually seen as a place for manufacturing, rather than design. However, there is also design activity in a factory that is devoted to the optimization of manufacturing processes. In this study, we highlight an alternative form of design that relies on a collective exploratory approach. A total of 30 projects from the Saint-Nazaire Airbus factory were selected and analyzed. Of these, two were selected as case studies to illustrate the factory's different design methods. Subsequently, quantitative analysis provided evidence of the existence of two design regimes: closed prescription and expandable prescription. The resulting solutions were examined, and it was found that designs under the expandable prescription regime provided more robust long-term solutions. This study offers new perspectives for reexamining innovation in manufacturing and exploring design activity on factory shop floors. [ABSTRACT FROM AUTHOR]

Mass customization (MC) is recognized as a new manufacturing paradigm for market competition, and several empirical studies have discussed elements of organizational structure that are conducive to MC. A previous study proposed a model of quality at source and identified cultural values that can be changed by cultural artifacts, such as the stop-the-line system and the Andon system. This paper explores the impacts of three groups of MC enabler variables (personalized design, modular design, and automated processes) on two internal dimensions of organizational culture (work cooperation and relationship harmony).This paper surveyed 160 samples across five manufacturing industries. The results confirm that the three MC enablers (personalized design, modular design, and automated processes) correlate positively with two internal dimensions of the organizational culture of Chinese manufacturers (work cooperation and relationship harmony). Of the two internal dimensions, work cooperation enhances organizational performance, while relationship harmony has no impact on organizational performance. Modular design, automated processes, and work cooperation are powerful tools in the implementation of MC and organizational performance. Personalized design and relationship harmony are useful in MC. However, these tools are intermediate and limited, and they do not contribute to the general performance of the entire organization. Thus, in terms of internal- and team-oriented cultural factors, work cooperation is more important than relationship harmony in the implementation of MC. Relationship harmony is a tool for managing work atmosphere, and this is a new characteristic feature of MC as a new operational paradigm. [ABSTRACT FROM AUTHOR]

The aim of this article is to present an overview of impurities of alkali metals and alkaline earth elements included in smelter-grade alumina and other raw materials that primarily report to the electrolyte, i.e., bath, and to suggest pathways for improved control at primary aluminum smelters. Comments are included on how these impurities affect intermediate subprocesses, metal products, and cell condition. The authors have worked to create a reference that not only reports on the scientific aspects of how impurities react in a bath of molten salt under electrolysis but also covers the practical matters of concern regarding impurities that affect the electrolyte. By combining scientific knowledge with process engineering techniques, readers should be able to better manage impurities and related impacts in aluminum production processes. [ABSTRACT FROM AUTHOR]

Within product development processes, computational models are used with increasing frequency. However, the use of those methods is often restricted to the area of focus, where product design, manufacturing process, and process chain simulations are regarded independently. In the use case of multi-material lightweight structures, the desired products have to meet several requirements regarding structural performance, weight, costs, and environment. Hence, manufacturing-related effects on the product as well as on costs and environment have to be considered in very early phases of the product development process in order to provide a computational concept that supports concurrent engineering. In this contribution, we present an integrated computational concept that includes product engineering and production engineering. In a multi-scale framework, it combines detailed finite element analyses of products and their related production process with process chain and factory simulations. Including surrogate models based on machine learning, a fast evaluation of production impacts and requirements can be realized. The proposed integrated computational product and production engineering concept is demonstrated in a use case study on the manufacturing of a multi-material structure. Within this study, a sheet metal forming process in combination with an injection molding process of short fiber reinforced plastics is investigated. Different sets of process parameters are evaluated virtually in terms of resulting structural properties, cycle times, and environmental impacts. [ABSTRACT FROM AUTHOR]

Accurate and timely investigation to concentrate grade and recovery is a premise of realizing automation control in a froth flotation process. This study seeks to use deep learning technologies modeling a manufacturing flotation process, forecasting the concentrate purities for iron and the waste silica. Considering the size and temporality of engineering data, we adopted a long short-term memory to form the core part of the deep learning model. To perform this process, 23 variables reflecting a flotation plant were monitored and collected hourly over a half year time span, then wrangled, split, and restructured for deep learning model use. A deep learning model encompassing a stacked long short-term memory architecture was designed, trained, and tested with prepared data. The model's performance on test data demonstrates the capability of our proposed model to predict real-time concentrate purities for iron and silica. Compared with a traditional machine model typified by a random forest model in this study, the proposed deep learning model is significantly more competent to model a manufacturing froth flotation process. Expected to lay a foundation for realizing automation control of the flotation process, this study should encourage deep learning in mineral processing engineering. [ABSTRACT FROM AUTHOR]

Possibilities of increasing the efficiency of technology for production of 8–16 (25) mm thick strip in strip mills having different consumer demand for hot-rolled sheet are demonstrated. Such production methods as redistribution of reductions in the roughing group stands, installation of induced cooling and heat protection screens on the intermediate roller table, rolling sheet of variable thickness ("wedgeshaped") in the finishing group of stands, make it possible to control temperature effectively both over strip length and thickness without use of external heat sources, and without loss of continuous hot rolling high productivity. [ABSTRACT FROM AUTHOR]

Establishing how to effectively manufacture cell therapies is an industry-level problem. Decentralised manufacturing is of increasing importance, and its challenges are recognised by healthcare regulators with deviations and comparability issues receiving specific attention from them. This paper is the first to report the deviations and other risks encountered when implementing the expansion of human pluripotent stem cells (hPSCs) in an automated three international site–decentralised manufacturing setting. An experimental demonstrator project expanded a human embryonal carcinoma cell line (2102Ep) at three development sites in France, Germany and the UK using the CompacT SelecT (Sartorius Stedim, Royston, UK) automated cell culture platform. Anticipated variations between sites spanned material input, features of the process itself and production system details including different quality management systems and personnel. Where possible, these were pre-addressed by implementing strategies including standardisation, cell bank mycoplasma testing and specific engineering and process improvements. However, despite such measures, unexpected deviations occurred between sites including software incompatibility and machine/process errors together with uncharacteristic contaminations. Many only became apparent during process proving or during the process run. Further, parameters including growth rate and viability discrepancies could only be determined post-run, preventing 'live' corrective measures. The work confirms the critical nature of approaches usually taken in Good Manufacturing Practice (GMP) manufacturing settings and especially emphasises the requirement for monitoring steps to be included within the production system. Real-time process monitoring coupled with carefully structured quality systems is essential for multiple site working including clarity of decision-making roles. Additionally, an over-reliance upon post-process visual microscopic comparisons has major limitations; it is difficult for non-experts to detect deleterious culture changes and such detection is slow. [ABSTRACT FROM AUTHOR]

Melt and cold crystallization characteristics of poly(3-hydroxybutyrate) (PHB) and poly(butylene adipate-co-terephthalate) (PBAT), two biodegradable polyesters of current industrial interest, as well as a PHB/PBAT blend, were investigated by nonisothermal tests of differential scanning calorimetry over a range of cooling/heating rates ranging between 2 and 64 °C min−1. Although more difficult to study the crystallization under isothermal conditions, the quantitative evaluation of nonisothermal crystallization is required to understand and model industrial processes, which are conducted under nonisothermal conditions. While PBAT crystallizes completely during cooling, PHB and the PHB/PBAT blend show incomplete crystallization from the melt, the process being completed during the reheating stage. Notwithstanding the different crystallization behavior, crystallinity levels and melting points of PHB, PBAT and the blend have virtually identical melt crystallization temperatures, due perhaps to differences in the nucleating efficiency of the stereoregular homopolymer PHB and the random copolymer PBAT. These findings may be of enough interest for process engineers designing and controlling operations. [ABSTRACT FROM AUTHOR]

Recent trends show that products are becoming more complex and multi-variant. Therefore, future production systems need to become more advanced in terms of reconfigurability, flexibility, and transformability. To achieve these advancements, future systems must be highly changeable and support plug-and-produce approaches. The majority of today's engineering methods focus on static workflows based on predefined assets and setups. As a consequence, changes in the production system come with high costs, especially during production process execution. Therefore, new engineering methods are required which are explicitly designed for highly changeable production systems. To contribute towards fully changeable production systems, an I4.0 framework is proposed that covers the entire engineering process. The focus is set on presenting a graphical I4.0-enabled engineering method that enables dynamic workflows with varying assets and setups. Moreover, in order to evaluate the method, a user study was conducted, in which participants were asked to solve multiple engineering tasks by utilizing the presented I4.0-enabled method as well as a conventional approach. The results indicated that the proposed I4.0-enabled engineering method significantly outperformed the conventional method in terms of required engineering times and subjective ratings. [ABSTRACT FROM AUTHOR]

Control charts are the most applicable tools for monitoring the quality of processes. The day-to-day changes in industrial processes and customers' expectations motivate the process engineers to monitor multiple correlated quality characteristics, simultaneously. Hence, in this paper, the design of a "double warning lines T2-Hotelling" control chart is studied because of the advantages of this multivariate control chart in detecting moderate and small shifts in a process. In this regard, this research aims to optimize a multi-objective economic–statistical design model that considers monitoring costs and statistical features of control chart, concurrently. The non-dominated sorting genetic algorithm II is utilized to obtain a suitable Pareto set for the model. Since it is difficult for the decision makers to select the most efficient solution among the Pareto set, three different methods of data envelopment analysis consisting of Charnes–Cooper–Rhodes model, cross-efficiency technique and aggressive formulation are used to rank the members of Pareto set and to select the most efficient one. Also, in this research the performance of these three methods in discriminating between the efficient solutions is compared to each other. Eventually, a comparative study is conducted to show the better performance of the suggested model in comparison with the corresponding economic design model. [ABSTRACT FROM AUTHOR]

This paper proposes a new type of assembly line worker assignment and balancing problem (ALWABP) which considers ergonomic risks. ALWABP occurs when task times vary according to the assigned worker. Although the operation time of a task is assumed to be fixed in classical assembly lines, it depends on the operator who executes the task in ALWABP. In ALWABP literature, the primary and secondary objectives are minimizing cycle time and balancing workload among workstations smoothly, respectively. When smoothing workload, only task times are taken into consideration in the relevant literature. However, degree of difficulty of tasks is also very important. Two workers executing two different stations with the same station time are assumed to be equally loaded according to the traditional perception. In fact, even they have the same station time; their workloads are different because of the different tasks they execute, in real life assembly line configurations. In order to close this gap between the real life and the literature, this study introduces an ALWABP problem with considering ergonomic risk factors (ErgoALWABP). Due to the complex nature of the problem, optimum seeking methods are not capable of solving it. So, the proposed problem is tackled with the multiple-rule based constructive randomized search approach. Also, OCcupational Repetitive Action method is used for making ergonomic risk assessment. Performance of the proposed solution procedure is compared with the relevant literature on benchmark data. Experimental results show that ergonomic environment could be improved when ergonomic risk factors are taken into account. [ABSTRACT FROM AUTHOR]

Biological collective systems have been an important source of inspiration for the design of production systems, due to their intrinsic characteristics. In this sense, several high level engineering design principles have been distilled and proposed on a wide number of reference system architectures for production systems. However, the application of bio-inspired concepts is often lost due to design and implementation choices or are simply used as heuristic approaches that solve specific hard optimization problems. This paper proposes a bio-inspired reference architecture for production systems, focused on highly dynamic environments, denominated BIO-inspired Self-Organising Architecture for Manufacturing (BIOSOARM). BIOSOARM aims to strictly adhere to bio-inspired principles. For this purpose, both shopfloor components and product parts are individualized and extended into the virtual environment as fully decoupled autonomous entities, where they interact and cooperate towards the emergence of a self-organising behaviour that leads to the emergence of the necessary production flows. BIOSOARM therefore introduces a fundamentally novel approach to production that decouples the system’s operation from eventual changes, uncertainty or even critical failures, while simultaneously ensures the performance levels and simplifies the deployment and reconfiguration procedures. BIOSOARM was tested into both flow-line and “job shop”-like scenarios to prove its applicability, robustness and performance, both under normal and highly dynamic conditions. [ABSTRACT FROM AUTHOR]

This paper presents an experimental parameter optimization of electrochemical honing process (ECH) on the surface finish generation capability on cast iron of ASTM 35 with Brinell Hardness Hb 212. Taguchi orthogonal array of L9 experiment is used for optimization. Results from the main effect plot, regression analysis, correlation analysis, and interaction plots for the means indicate that best surface finish is obtained where the electric voltage is 15 V, electrolyte concentration is 20%, electrolyte pressure is 0.667 Mpa, and motor rotational speed is 60 rpm. However, significant variation is seen in the control of electric voltage as compared to the other three. Higher signal-to-noise ratio is observed on electric voltage followed by electrolyte concentration and electrolyte pressure signifying electric voltage is the determining factor. From standard deviation analysis, electrolyte pressure and electrolyte concentration are found to need close attention for better surface roughness along with electric voltage. The interaction plot for the three factors also indicates that electric voltage at highest level is more significant than the other factors. However, it is noted that the interaction of the electric voltage, electrolyte concentration, and electrolyte pressure significantly determines the effectiveness of the ECH process. Meanwhile, the level of control between electrolyte pressure and electrolyte concentration needs careful attention as the two factors work against each other. [ABSTRACT FROM AUTHOR]

Knowledge of material properties, microstructure, underlying material composition, and manufacturing process parameters that the material has undergone is of significant interest to materials scientists and engineers. A large amount of information of this nature is available in publications in the form of experimental measurements, simulation results, etc. However, getting to the right information of this kind that is relevant for a given problem on hand is a non-trivial task. First, an engineer has to go through a large collection of documents to select the right ones. Then, the engineer has to scan through these selected documents to extract relevant pieces of information. Our goal is to help automate some of these steps. Traditional search engines are not of much help here, as they are keyword centric and weak on relation processing. In this paper, we present a domain-specific search engine that processes relations to significantly improve search accuracy. The engine preprocesses material publication repositories to extract entities such as material compositions, material properties, manufacturing processes, process parameters, and their values and builds an index using these entities and values. The engine then uses this index to process user queries to retrieve relevant publication fragments. It provides a domain-specific query language with relational and logical operators to compose complex queries. We have conducted an experiment on a small library of publications on steel on which searches such as “get the list of publications which have carbon composition between 0.2 and 0.3 and on which tempering is carried out for about 30 to 40 min” are performed. We compare the results of our search engine with the results of a keyword-based search engine. [ABSTRACT FROM AUTHOR]

A multi-agent based system is proposed to simultaneous scheduling of flexible machine groups and material handling system working under a manufacturing dynamic environment. The proposed model is designed by means of $$\hbox {Prometheus}^{\mathrm{TM}}$$ methodology and programmed in $$\hbox {JACK}^{\mathrm{TM}}$$ agent based systems development environment. Each agent in the model is autonomous and has an ability to cooperate and negotiate with the other agents in the system. Due to these abilities of agents, the structure of the system is more suitable to handle dynamic events. The proposed dynamic scheduling system is tested on several test problems the literature and the results are quite satisfactory because it generates effective schedules for both dynamic cases in the real time and static problem sets. Although the model is designed as an online method and has a dynamic structure, obtained schedule performance parameters are very close to those obtained from offline optimization based algorithms. [ABSTRACT FROM AUTHOR]

In assembly activities, performing assembly planning is a crucial issue for the human-centered manufacturing. The challenges involve in retrieving and utilizing the real-time data about human-based work activities in a shop floor. Instead of the simulation-based assembly planning, the marker-based motion capture system can acquire realistic motion data of workers in assembling sites, but this method is inclined to corrupt due to the occlusion and is troublesome to be installed within the shop floor. Therefore, based on the complement of the optical and inertial sensor, this paper presents a self-contained motion capture method for assembly planning in real shop floor. It can provide a real-time and portable motion capturing for workers, avoiding the failure of traditional outside-in motion capture system due to occlusions or incorrect installations. What is more, the portable motion capture method can run on consumer mobile devices, providing a convenient and low-cost way to perceive the workers' motion in shop floor, which is significant for extensive applications in assembly verification and planning for digital factories. Finally, experiments are carried out to demonstrate the accuracy and feasibility of the proposed motion capture method for assembly activities. [ABSTRACT FROM AUTHOR]

Cellular bucket brigade (CBB) is known as the self-organizing and self-balancing production system, but in different constraints, its self-organizing feature also presents different characteristics. According to constraints of station, this article divides the CBB system into three types: (1) CBB-1, no obvious location, in which an arbitrary position can be an exchange of work; (2) CBB-2, location limited, in which any place can be a transition; and (3) CBB-3, location limited, which cannot be exchanged within the stations. Then, the corresponding mathematical models are established to analyze the performance of the CBBs. At last, numerical simulation provides the following results: Both CBB-1 and CBB-2 have only one balance point and good convergence from any states to balance point, while the balance point of CBB-3 is of uncertainty. [ABSTRACT FROM AUTHOR]

Modern manufacturing systems are expected to be flexible and efficient in order to cope with challenging market demands. Thus, they must be flexible enough as to meet changing requirements such as changes in production, energy efficiency, performance optimization, fault tolerance to process or controller faults, among others. Demanding requirements can be defined as a set of quality of service (QoS) requirements to be met. This paper proposes a generic and customizable multi-agent architecture that, making use of distributed agents, monitors QoS, triggering, if needed, a reconfiguration of the control system to recover QoS. As a proof of concept, the architecture has been implemented to provide availability of the control system understood as service continuity. The prototype has been tested in a case study consisting of an assembly cell where assessment of the approach has been conducted. [ABSTRACT FROM AUTHOR]

Automotive industry faces new challenges every day, new design trends and technological deployments from research push companies to develop new models and facelifts in short term, requiring new tools or tool reshaping. Concerning the current world economic scenario, decreasing time for tooling up becomes as important as decreasing time-to-market. Such scenario opens up the horizons for new manufacturing approaches like additive manufacturing, in this case, applied for tooling up a stamping process on the automotive industry for the production of body panels. This approach enables the manufacturing of stamping inserts using similar high performance alloy steel as in conventional tooling, therefore, without losing tool mechanical properties. The stamping tools produced were tested by an automotive company in order to determine tool behaviour under real operating conditions, considering the high level demands of the stamping process. The results obtained enabled to conclude that metal additive manufacturing provided tools for the stamping process with excellent performance with a significant decrease on time-to-tooling. [ABSTRACT FROM AUTHOR]

The majority of the current product configurators defined for the small or medium-sized enterprise one-of-a-kind production (SME OKP) with the dominant variation of the product by typology are derived from the assemble-to-order (ATO) production configurators. Unfortunately, they do not provide the customers with the possibility to adjust the products to their specific needs and further configuration-related actions through specialized software interfaces are required. On the basis of a detailed 1-year-long customer behavior tracking and analysis, the following key issues of the actual configurators have been defined: a low degree of the product adjustment, the complexity of the process of modeling the adjusted product, the extension of the leading time, a separated process of modeling, and the establishment of the communication channel between the customer and the manufacturer in the real time. The proposed solution is based on integrating the existing configurators into one common software application. It should act mainly as the necessary real-time communication channel between the customer and manufacturer in order to alleviate the effects of the product complex paradox. With this concept, the reduction of the leading time is observed as the additional positive effect. The case study illustrates the basic principles and technology required for the practical realization of the proposed solution for the configuration processes of the products in the SME OKP for the PVC windows manufacturing in the hybrid manufacturing cloud environment. [ABSTRACT FROM AUTHOR]

Real-time manufacturing data plays more and more important roles in today's competitive manufacturing industry; however, many enterprises are still troubled by the lack of this timely, accurate, and consistent manufacturing data as there are no effective data collecting and process methods. The hysteretic and unmatched information flows lead to great opacity and uncertainty for production management. This paper thereby proposes a comprehensive real-time data-driven monitoring method in job-shop floor based on radio frequency identification (RFID) technology to address these issues. Firstly, a RFID configuration strategy is put forward including both RFID tag and device configuration schemas. The essence of RFID applications in job-shop floor is revealed too. Next, different levels of data collecting and monitoring models are established one by one, from single RFID reader level to process and process flow levels, wherein different types of state blocks are deployed to a decomposed process/process flow, generating a series of continuous event-driven data collecting units (EDCUs), which not only specify how to collect real-time on-site data but also point out what data should be collected. Then, three data processing methods are presented for different situations such as data preprocessing, fusion, and exception handling. Finally, a use case of a typical part is studied based on a prototype system which demonstrates how to use the proposed models and methods to monitor the production process of the part in job-shop floor and shows their feasibility simultaneously. [ABSTRACT FROM AUTHOR]

The incremental sheet forming processes (ISF) are attracting lots of attentions due to their advantages on rapid prototyping, without special dies and short lead time. The numerical simulation can be a valid method to investigate the forming process and predict the defects. In this study, an extended fully coupled ductile damage model with mixed nonlinear hardening was used to simulate the ISF process. At the same time, the yield surface distortion was also considered in this model, which can enhance the capability of modeling metallic material behavior under complex loading paths. Afterwards, some simulations were conducted with the proposed model. Additionally, one tension-shear orthogonal loading test was assigned on the one representative element in order to investigate the loading path effect during ISF process. By comparing the equivalent plastic strain and ductile damage evolution of the blank, the influence of the yield surface distortion on the ISF process was proved. [ABSTRACT FROM AUTHOR]

The grinding process is still an important manufacturing process for the machining of automotive components. For power train components, ultra-high carbon steel (UHC-steel) is a promising new innovative alloy because of its low specific density. Results from turning of UHC-steel showed that the texture of UHC-steel significantly differs from conventional steels. Furthermore, extremely hard carbides, which are embedded into a soft ferrite matrix, result in a UHC-steel specific machining behavior and a high tool wear rate. Therefore, UHC-steel is marked as a difficult-to-cut material. So far, there are no research results available for the grinding of UHC-steel. Therefore, fundamental investigations were conducted in order to analyze the material removal and chip formation mechanisms. Scratching tests with a geometrically defined cubic boron nitride cutting edge showed ductile material removal mechanisms for a single grain chip thickness variation from h = 1.5 up to 14 μm. Analysis of the contact zone by means of an innovative quick stop device confirms these results. [ABSTRACT FROM AUTHOR]

The integrated manufacturing system is one of the foremost operational strategies adapted by manufacturing organizations to overcome environmental and manufacturing uncertainties and to come out from global economic crisis. Adding value to the manufacturing industry in terms of sustainability and also in compliance with the requirement of the stakeholders, a new approach was designed by developing an integrated model. In this paper, the authors have adopted various literature reviews to develop an integrated model for manufacturing industries called integrated manufacturing business excellence system. The integrated manufacturing business excellence system is nothing but a bundle of global manufacturing management concepts, namely total quality management, total productive maintenance, corporate social responsibility, knowledge management, lean manufacturing, agile manufacturing, and sustainable manufacturing. The proposed model comprises of ten constructs, namely visionary leadership and management commitment, systematic approach to management, customer focus and satisfaction, continuous improvement and innovation, workforce management, manufacturing strategy, manufacturing practice audit system, and technology management and information system. In order to test the proposed framework by empirical means, a research instrument was constructed with a total number of 91 items identified under the above ten constructs of integrated manufacturing business excellence system model and collected data scientifically. The psychometric test results of our data set are within defined ranges. Further, we performed a confirmatory analysis to check the validity of ten constructs. The results of multivariate analysis suggest that the proposed ten constructs are valid. The model has a good fit based on goodness of fit indices obtained through structural equation modeling approach. [ABSTRACT FROM AUTHOR]

This paper offers a review of univariate and multivariate process capability indices (PCIs). PCIs are statistic indicators widely used in the industry to quantify the capability of production processes by relating the variability of the measures of the product characteristics with the admissible one. Univariate PCIs involve single-product characteristics while multivariate PCIs deal with the multivariate case. When analyzing the capability of processes, decision makers of the industry may choose one PCI among all the PCIs existing in the literature depending on different criteria. In this article, we describe, cluster, and discuss univariate and multivariate PCIs. To cluster the PCIs, we identify three classes of characteristics: in the first class, the characteristics related to the information of the process data input are included; the second class includes characteristics related to the approach used to calculate the PCIs; and in the third class, we find characteristics related to the information that the PCIs give. We discuss the strengths and weaknesses of each PCI using four criteria: calculation complexity, globality of the index, relation to proportion of nonconforming parts, and robustness of the index. Finally, we propose a framework that may help practitioners and decision makers of the industry to select PCIs. [ABSTRACT FROM AUTHOR]

High accuracy manufacturing requires the utilisation of advanced signal processing and analytics to monitor, manage, and control production processes. These systems vary in size, scope, and complexity and have traditionally required the skill of multi-disciplinary individuals, for end-to-end application. Current research trends in digital manufacturing aim to remove this complexity through interoperability solutions encapsulated in cyber physical systems. These systems provide a platform for real-time heterogeneous data acquisition, analysis, and distribution. The focus of this research is to demonstrate the application of a cyber physical process monitoring system within an industrial case study. Specifically, a multi-scalable signal processing and analytic system is developed, for both user-driven and semi-autonomous production decision support in CNC turning machining. [ABSTRACT FROM AUTHOR]

The needs for damage-free and fine-scale features with good surface finish have been challenging today's manufacturing technologies. Laser machining process performed under a flowing water layer is a capable technique to satisfy these requirements with high processing rate and clean cut surface. However, the capability and performance of this process for milling applications have not clearly been understood yet. Therefore, this study aims at enabling an insight into the laser milling process under a flowing water layer. Titanium alloy (Ti-6Al-4V) was employed as a work sample in this study, and a nanosecond pulse laser was used to ablate the material in water. The effects of laser traverse speed and number of scans on geometrical dimensions, surface and subsurface characteristics were experimentally investigated. The results revealed that a deeper milled cavity with a smaller taper angle was achievable by using a slower traverse speed and more number of laser scans. A trade-off between the uniformity and roughness of milled surface was also evidenced under the different laser traverse speeds examined in this study. By comparing to the laser milling of titanium alloy in ambient air, there was no metallurgical change remarkably found in the laser-milled area when the process was carried out in water. In addition, specific energy required to fabricate a laser-milled cavity was about 18 kWs/mm for a single scan technique and linearly increased with the number of scans. The findings of this study will advance the understanding of laser ablation in flowing water as well as other liquid-assisted laser machining techniques. The implication of this study will further open wider applications of liquid-assisted laser ablation for a more intricate micro-fabrication with high resolution, high processing rate, and less thermal damage. [ABSTRACT FROM AUTHOR]

The form error in manufactured parts needs to be assessed to verify the compliance of the parts with the specifications. Workpieces are usually measured by means of a coordinate measuring machine that extracts a set of three-dimensional points from the manufactured surface. It is obvious that the association method used to fit the nominal shape to the set of points plays an essential role in the error assessment process. Moreover, the uncertainty that arises during the measurement procedure must be estimated to provide a complete measurement result. Within this framework, the aim of this paper is to compare the performances of the so-called probabilistic method with those of the classical least squares methods in order to estimate different roundness errors together with the associated uncertainty. The latter has been estimated by means of two different approaches: the bootstrap and the so-called gradient-based method, and the differences between the two are discussed. [ABSTRACT FROM AUTHOR]

Measurements are the core of quality systems. The calibration of the measurement devices is a form of evaluating it. The variability of these measurement devices is verified to know the variation inherited in the measurement tool. Additionally, the dynamics of the actual production systems cannot be satisfied by the classic approaches of the human visual inspection. This happens because they exceed the human capacities, and this phenomenon causes the loss of reliability at the outputs of the system. This paper presents a hybrid model of adaptive neuro-fuzzy inference system (ANFIS) to evaluate quality features. Also, for this purpose, it offers knowledge-based expert system able to do the quality assurance tasks by learning and adaptation. The obtained results provide an acceptable error rate for this class of systems to run at the speed of the actual manufacturing system. [ABSTRACT FROM AUTHOR]

In order to achieve a high level of product quality, it is imperative to gain a high degree of predictability especially in automated manufacturing setup. Surface finish is one of the most important measures for determining the quality of products in machining. Therefore, accurate predictive models for surface finish are needed. This paper utilizes vibration signals that are experimentally obtained during the end milling of aluminum plates at different cutting conditions. Several features are extracted by processing the acquired signals in both the time and frequency domains. The feature sets include statistical parameters, fast Fourier transforms (FFT) spectra, and the wavelet packets. This work introduces a classifier based on a support vector machine to analyze the set of features in order to predict the type of surface finish. Experiments are conducted for three different types of kernels and parameter configurations. One objective is to examine the effect of feature reduction on the performance of the proposed classifier using three different feature selection algorithms. Another objective is to compare the results with k-nearest neighbor, decision tree, and random forest classifiers. The results show the effectiveness of feature reduction and support vector machine in the success of the proposed classifier. [ABSTRACT FROM AUTHOR]

Controlling product geometric quality is an important issue, because real parts deviate from their nominal value (e.g., in form, orientation, and position error of features, size of part, etc.). To analyze the influence of these deviations on final product, one solution is to consider the nonnominal Skin Model Shape to simulate assembly, manufacturing, or metrology. The modeling of nonnominal parts is still in its initial phases. First, methods of generating a single feature with deviations are reviewed and classified. With the combination of the single nonideal features to obtain the complete nonideal model of the part, geometrical issues appear, such as gaps and self-intersections. These can be influenced by acute and obtuse angles and the ratio between mesh size and deviation value. From an analysis of these issues, two deviation combination methods are proposed to preserve the manufacturing deviation of features and consistency of the model. These methods are qualified as local and global methods. The local method is based on the iterative calculation of mesh regularization. The global method is based on finite element analysis, with manufacturing deviations added to the nominal model by the penalty function approach. The effectiveness and efficiency of both kinds of method are compared on a trial geometry. The global method is preferred as it needs no iterative calculation, no stop criteria and gives better results. Finally, the proposed method is validated on a more complex mechanical part: a cutter body. [ABSTRACT FROM AUTHOR]

The industrial sector is increasingly concerned with energy consumption, due to the environmental burden and increased cost. An action plan requires the study of energy efficiency in manufacturing processes, especially energy-intensive processes. The energy consumption, during the assembly, plays a significant role on the product's final energy and eco-evaluation. In this paper, there is a presentation of an in-depth study of the energy efficiency of joining processes. The laser welding process is also discussed in detail, since it has been an increasingly indispensable part of competitive manufacturing throughout the world, and it is a thermal process with relatively low energy efficiency. Important outcomes, regarding the dependence of energy efficiency and weld pool geometry on process parameters, have been derived. [ABSTRACT FROM AUTHOR]

This paper presents the integration of a robotic system in a human-centered environment, as it can be found in the shoe manufacturing industry. Fashion footwear is nowadays mainly handcrafted due to the big amount of small production tasks. Therefore, the introduction of intelligent robotic systems in this industry may contribute to automate and improve the manual production steps, such us polishing, cleaning, packaging, and visual inspection. Due to the high complexity of the manual tasks in shoe production, cooperative robotic systems (which can work in collaboration with humans) are required. Thus, the focus of the robot lays on grasping, collision detection, and avoidance, as well as on considering the human intervention to supervise the work being performed. For this research, the robot has been equipped with a Kinect camera and a wrist force/ torque sensor so that it is able to detect human interaction and the dynamic environment in order to modify the robot's behavior. To illustrate the applicability of the proposed approach, this work presents the experimental results obtained for two actual platforms, which are located at different research laboratories, that share similarities in their morphology, sensor equipment and actuation system. [ABSTRACT FROM AUTHOR]

Selective laser melting (SLM) as a part of 3D printing technology has been a novel industrial manufacturing process nowadays. However, the collection of metal powders emitted from the working plane is significant for the SLM process. The uniformity of the flow passing through the SLM working chamber, which helps collect emitted powders, has been considered as a key solution. In this study, for the purpose of improving the flow uniformity, a blow-to-suction device composed of a trapezoid push nozzle, a working chamber, and a suction tunnel was applied. Various parameters, such as the width of trapezoid push nozzle, the width of suction tunnel, and the nozzle-to-plane distances, were examined experimentally and computationally. Hot-wire velocity measurement and smoke flow visualization were used to verify the reliability of the simulation. Through the results of degree of uniformity (DOU), the momentum exchange between the suction and blow sides plays an important role for producing a uniform flow through the working chamber. In addition, higher suction velocity as well as larger nozzle-to-plane distance result in relatively better uniformity of the flow. [ABSTRACT FROM AUTHOR]

The objective of this paper is to examine the effect of prognosis agent technology (PAT) on manufacturing organization's productivity and control. Extant literature advocates that various agents have been developed in the paradigms of designing, diagnosis, production, marketing, etc., but research on the effect of PAT on organizational output has not been explored yet. This paper uses the construct of PAT and checks its effect on performance of organizations. The research utilizes data collected from various manufacturing organizations. Based on literature survey, a set of hypotheses were proposed. Then, exploratory and confirmatory factor analyses were performed on collected data. Thereafter, a hypothetical model on PAT comprising five factors (manufacturing processes, fault identification, integration of manufacturing system with maintenance, manufacturing organization's productivity, and control) is developed using structural equation modeling. All the hypotheses formed were supported, which indicates that the use of PAT in manufacturing organizations does increase organizational productivity and manufacturing control. [ABSTRACT FROM AUTHOR]

Manufacturing methods using molds, such as casting and injection molding, are widely used in industries. A basic requirement when using such manufacturing methods is that design engineers must design products so that they incorporate certain geometrical features that allow the mold parts to be removed from the created solid object. In the present study, we propose a manufacturability evaluation method especially adapted for the use of molds. To evaluate the manufacturability, we introduce fictitious physical models that are described by steady-state anisotropic advection-diffusion equations. In these fictitious physical models, material domains have a virtual source term and the advection directions are aligned with the directions along which the mold parts are parted. Void regions, where the values of all fictitious physical fields are high, then represent either undercut geometries that would prevent the mold from being released, or interior voids that cannot be cast. Consequently, manufacturability can be evaluated using these fictitious physical fields. Furthermore, in the present study, we integrate this evaluation method with topology optimization and propose a scheme for imposing a molding constraint within the topology optimization procedure. This newly proposed topology optimization method can consider the position of mold parting lines prior to the detailed optimization procedure. Several numerical examples are provided to demonstrate the validity and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Flexibility and agility are principles increasingly necessary and used in current automotive manufacturing processes due to the market paradigm change, going from mass production to customized one. Some countries, where the human labour cost is very attractive, design processes depending essentially on the workers' performance. However, some risks can be induced by the use of intensive labour due to uncertainties related to human behaviour and fatigue. Small assembly operations comprising a large variety of models and short cycle time are usually carried out manually, due to their flexibility and agility. However, critical factors such as quality, commitment with the delivery time, and increase of labour costs become attractive factors to start developing flexible and agile equipment that allows simple set-up, short cycle time, and traceability. Robotics is widely used to cover these purposes, but the required space to operate with a robot and the cost involved (which will need tools as an automatic equipment) make unfeasible its use in some applications. [ABSTRACT FROM AUTHOR]

Recently, sustainable development has obtained increasing attentions from governments, industry, and academia owing to the limited natural resources. In the area of energy consumption, manufacturing accounts for a major portion of the total energy usage in industry. There is a clear necessity for energy-efficient manufacturing by optimizing manufacturing activities. Condition monitoring is the technology that provides runtime information for optimization. This paper aims to provide a better understanding of past achievements and future trends of condition monitoring towards energy-efficient manufacturing. Since there are a variety of sensors and technologies that can be used for condition monitoring towards energy-efficient manufacturing, this paper divides manufacturing activities into three levels, namely unit process level, shop-floor level, and supply chain level, and summarizes and discusses the sensors and technologies required to enable energy-efficient manufacturing on each level. With the advancement of technology, condition monitoring shows the characteristic of intelligence. Intelligent sensors that can be applied to condition monitoring in energy-efficient manufacturing are also reviewed. This paper can be helpful to manufacturers who are willing to improve energy efficiency in own manufacturing practice. [ABSTRACT FROM AUTHOR]

Process planning and scheduling are two major sub-systems in a modern manufacturing system. In traditional manufacturing system, they were regarded as the separate tasks to perform sequentially. However, considering their complementarity, integrating process planning and scheduling can further improve the performance of a manufacturing system. Meanwhile, the multiple objectives are needed to be considered during the realistic decision-making process in a manufacturing system. Based on the above requirements from the real manufacturing system, developing effective methods to deal with the multi-objective integrated process planning and scheduling (MOIPPS) problem becomes more and more important. Therefore, this research proposes a multi-objective genetic algorithm based on immune principle and external archive (MOGA-IE) to solve the MOIPPS problem. In MOGA-IE, the fast non-dominated sorting approach used in NSGA-II is utilized as the fitness assignment scheme and the immune principle is exploited to maintain the diversity of the population and prevent the premature condition. Moreover, the external archive is employed to store and maintain the Pareto solutions during the evolutionary process. Effective genetic operators are also designed for MOIPPS. To test the performance of the proposed algorithm, three different scale instances have been employed. And the proposed method is also compared with other previous algorithms in literature. The results show that the proposed algorithm has achieved good improvement and outperforms the other algorithms. [ABSTRACT FROM AUTHOR]

Even if more reliable than the past, the performance of modern manufacturing systems is still affected by machine's deteriorations and breakdowns. As a consequence, adequate maintenance programs must be implemented to adequately satisfy demands during manufacturing stops due to unexpected failures or preventive maintenance (PM) actions. Despite production and maintenance are closely related issues, their joint optimization has become an important research topic just during the last decade. Therefore, the present paper proposes a model for the combined optimization of production/inventory control and PM policies with the aim of minimizing the total expected cost per unit time. The model is formulated referring to a continuous production system characterized by a random deteriorating behavior so that the presence of a buffer is considered to ensure a continuous products supply during interruptions of service caused by breakdowns or planned maintenance actions on the production system. Unlike the main part of the existing literature, non-restriction on the failure occurrence is here forced, namely that the manufacturing system may fail at any age within the production cycle as well as more than one failure may occur during the same period. A Simulated Annealing-based algorithm combined with a Monte Carlo simulation module is proposed as a resolution approach. The robustness of the developed algorithm is demonstrated by means of repeated runs of different simulated scenarios characterized by diverse sets of cost parameters. Results also confirm the effectiveness of the proposed three-level theoretical inventory profile. [ABSTRACT FROM AUTHOR]

Cloud manufacturing (CMfg) provides a new product development model in which users are enabled to configure, select, and utilize customized manufacturing services on-demand. The service composition with optimal overall quality of service (QoS) is of great significance since it affects the efficiency of resource sharing and optimal allocation in CMfg systems. However, some limitations still exist in manufacturing service composition methods especially in the complicated cloud environment. This owes to two aspects: (1) current service composition approaches assume that the QoS of services is fixed and not influenced by other services, the existence of the service correlation context is not considered adequately, thus resulting in no accordance with practical applications; (2) with the growing number of candidate services in cloud resource pools, the traditional methods might be inefficient for addressing large scale service composition problems. To overcome such drawbacks, this study proposes a new hybrid teaching-learning-based optimization (HTLBO) algorithm for optimal service composition with the consideration of service correlations. Experiments are conducted to verify the effectiveness and feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Mass customization as a state-of-the-art production paradigm aims to produce individualized, highly variant products and services with nearly mass production costs. A major side-effect for companies providing complex products and services is that customers quite often get confused by the high variety and do not make a purchase. Personalization technologies can help to alleviate the challenges of mass customization. These technologies support customers in specifying products and services that fit their wishes and needs in a fashion where decision and interaction efforts with sales support systems are significantly reduced. We provide a short overview of related research and the articles that are part of this special issue on Personalization and Mass Customization. [ABSTRACT FROM AUTHOR]

In many manufacturing processes, study variable is not the only quality characteristic, but there may exist some explanatory variable(s) that are associated with the study variable. This association may be linear or nonlinear depending on the nature of variables. The term profiling is used for such relationships among study and explanatory variables. Linear profiles are more common options because of their simplicity and coverage of more common scenarios. A popular proposal for the monitoring of linear profiles is EWMA − 3 chart that detect shifts in the profile parameters including slope, intercept, and error variance. The said chart is designed under simple random sampling. In this study, we have designed and investigated EWMA − 3 chart under the different ranked set sampling strategies ( τ) such as ranked set sampling (RSS), median ranked set sampling (MRSS), extreme ranked set sampling (ERSS), double ranked set sampling (DRSS), double median ranked set sampling (DMRSS), and double extreme ranked set sampling (DERSS). We have used average run length (ARL), extra quadratic loss (EQL), relative average run length (RARL), and performance comparison index (PCI) as performance measures for the aforementioned designs of EWMA − 3 chart under different sampling schemes. The computational results of run length properties revealed that the ranked set based EWMA − 3 chart offers better detection ability. More specifically, EWMA − 3 and EWMA − 3 serve the purpose in a more efficient way. [ABSTRACT FROM AUTHOR]

Chemo-mechanical-grinding (CMG) is a hybrid process which integrates chemical reaction and mechanical grinding between abrasives and workpiece into one process. It has been successfully applied into manufacturing process of silicon wafers where both geometric accuracy and surface quality are required. This paper aims to study the potential of CMG process in manufacturing process of single crystal sapphire wafers. The basic material removal mechanism in terms of chemical effect and mechanical effect in CMG process has been analysed based on experiment results of two different kinds of CMG wheels. The experiment results suggest that chromium oxide (CrO) performs better than silica (SiO) in both material removal rate (MRR) and surface quality. It also reveals that, no matter under dry condition or wet condition, CMG is with potential to achieve excellent surface quality and impressive geometric accuracy of sapphire wafer. Meanwhile, test result by Raman spectrum shows that, by using CrO as abrasive, the sub-surface damage of sapphire wafer is hardly to be detected. Transmission electron microscopy (TEM) tells that the sub-surface damage, about less than 50 nm, might remain on the top surface if chemical effect is not sufficient enough to meet the balance with mechanical effect in CMG process. [ABSTRACT FROM AUTHOR]

The objective of this research is to develop on-stream inspection (OSI) system for pitting corrosion defect for intelligent and safe manufacturing. During the tests of two pressure vessels, acoustic emission (AE) was utilized for on-line detection. Phase array ultrasonic inspection was also conducted in order to assess internal integrity of pressure vessels. Feature acquisition was utilized to obtain essential features from the experimental data. In order to obtain the optimal features effectively, Euclidean distance measure and sequential forward search algorithm (SFS) were utilized for choosing features. The chosen three features were AE time-domain kurtosis, AE duration, and AE frequency domain average. Adaptive neuro-fuzzy inference systems (ANFIS), which is a branch of artificial intelligence (AI), were utilized. The chosen three features were the inputs to a 3*(3*3*3) ANFIS. Whether there is pitting corrosion defect or not was the output of this system. This approach can most quickly and most reliably determine whether there is a pitting corrosion defect or not for pressure vessels. With phase array ultrasonic system for on-line inspection, the most reliable and accurate verification of the OSI can be conducted. The developed intelligent on-line system has very high reliability and safety. This OSI system can reduce shut down inspection (SDI), increase automation, efficiency, and reduce cost for intelligent and safe manufacturing. [ABSTRACT FROM AUTHOR]