Search

This review article focuses on the design and development of various processes, with an emphasis over the use of simulation abilities as a tool that helps the continuous improvement of manufacturing. The examination of common techniques to modelling production systems is the focus of such work. Simulation is a strong tool that allows businesses to save time and money. It enables user to evaluate various strategies and analyse the operation without even affecting actual system. This review paper investigates previous research to implement effective solution on production line in Ujas electrical pvt. Ltd. Many benefits may be gained by employing the simulation technique, which including reduced time spent changing the industrial layout, cost savings, increased profit, increased productivity, reduced idle time, reduced lead time, and so on.

Customers in the manufacturing sector, especially in the automotive industry, have a high demand for individualized products at price levels comparable to traditional mass-production. The contrary objectives of providing a variety of products and operating at minimum costs have introduced a high degree of production planning and control mechanisms based on a stable order sequence for mixed-model assembly lines. A major threat to this development is sequence scrambling, triggered by both operational and product-related root causes. Despite the introduction of Just-in-time and fixed production times, the problem of sequence scrambling remains partially unresolved in the automotive industry. Negative downstream effects range from disruptions in the Just-in-sequence supply chain, to a discontinuation of the production process. A precise prediction of sequence deviations at an early stage allows the introduction of counteractions to stabilize the sequence before disorder emerges. While procedural causes are widely addressed in research, the work at hand requires a different perspective involving a product-related view. Built on unique data from a real-world global automotive manufacturer, a supervised classification model is trained and evaluated. This includes all the necessary steps to design, implement, and assess an AI-artifact, as well as data gathering, preprocessing, algorithm selection, and evaluation. To ensure long-term prediction stability, we include a continuous learning module to counter data drifts. We show that up to 50% of the major deviations can be predicted in advance. However, we do not consider any process-related information, such as machine conditions and shift plans, but solely focus on the exploitation of product features like body type, power train, color, and special equipment.

International audience; The Marie-Clémence-Fouriaux street site fills an extensive gap of data from Reims related to ancient glass workshops. This data set completes our knowledge relative to the construction methods for furnace manufacturing. Although they are based on a standard model, the furnaces possess characteristics tying them to local construction traditions, as well as local resources. The waste materials identified indicate that these workshops produced bluish, yellow, and greenish glass vases in the late 1st c. AD, as well as colorless and blue-green glass vases during the 3rd c. AD, very likely of small dimension (balsams or small prismatic bottles).; Le site de la rue Marie-Clémence-Fouriaux vient combler la longue absence de données rémoises sur les ateliers de verriers antiques et complète les connaissances sur la mise en oeuvre des fours de fabrication. Bien que d’un modèle standard, ils possèdent des caractéristiques propres aux traditions locales de construction et liées aux ressources présentes dans leur environnement. Les déchets découverts indiquent que ces ateliers produisaient des vases en verre bleuté, jaune et verdâtre à la fin du Ier s. apr. J.-C. et des vases en verre incolore et bleu-vert au IIIe s. apr. J.-C., certainement des petits contenants (balsamaires ou petites bouteilles prismatiques).

[ES] La creciente demanda de coches eléctricos e híbridos, tanto en el ámbito nacional como internacional, ha generado la necesidad de aumentar los volúmenes de producción de los componentes necesarios para la fabricación de estos. El presente trabajo, nace de esta necesidad y del proyecto que la empresa Instalaciones Eléctricas Mafelec S.L., empresa donde la alumna ha realizado sus prácticas, está llevando a cabo en la Planta de Baterías de la Factoría Ford Almussafes. El objetivo, por tanto, de este proyecto es el de rediseñar la línea actual de fabricación de baterías PHEV para adaptarla a la situación futura donde se requiere conseguir una reducción de 63 segundos del tiempo de ciclo actual. Para ello, se realizará un rebalanceo de procesos del problema GALBP presentado, donde se hará uso de heurísticas específicas para su resolución. Una vez finalizado el proceso de equilibrado de la línea, se procederá a simular esta nueva situación haciendo uso del software JaamSim, esto permitirá por un lado comprobar que se ha realizado un correcto rebalanceo de procesos, y por otro, analizar esta nueva situación y proponer mejoras para las estaciones cuello de botella. Finalmente, estas mejoras serán introducidas en el modelo de simulación para ayudar en la elección de la mejora más apropiada., [CAT] La creixent demanda de cotxes elèctrics i híbrids, tant en l’àmbit nacional com internacional, ha generat la necessitat d’augmentar els volums de producció dels components necessaris per a la fabricació d’aquests. El present treball, naix d’aquesta necessitat i del projecte que la empresa Instalaciones Eléctricas Mafelec S.L., empresa on l’alumna ha realitzat les seues pràctiques, està duent a terme en la Planta de Bateries de la Factoria Ford España. L’objectiu, per tant, d’aquest projecte es el de realitzar un redisseny de la línia actual de fabricació de bateries PHEV per tal d’adaptar-la a la situació futura la qual requereix una reducció del temps de cicle de 63 segons respecte al temps de cicle actual. Per tal d’aconseguir aquest objectiu, es realitzarà un equilibrat del problema GALBP presentat, per al qual es farà us de heurístiques específiques per tal de resoldre’l. Una vegada finalitzar el procés d’equilibrat de la línia, es passarà a realitzar la simulació d’aquesta, fent us del software de simulació JaamSim. Açò permetrà, per una banda comprovar que l’equilibrat de la línia s’ha fet correctament, y per altra, analitzar la nova situació i proposar millores per a les estacions coll de botella. Finalment, aquestes millores seran introduïdes en el model de simulació per tal d’ajudar en la elecció de la millora més apropiada., [EN] The growing demand for electric and hybrid cars, both nationally and internationally, has generated the need to increase the production volumes of the components needed to manufacture them. This work arises from this need and from the project that the company Instalaciones Eléctricas Mafelec S.L., the company where the student has done her internship, is carrying out in the Battery Plant of the Ford Factory in Spain. The objective, therefore, of this project is to redesign the current PHEV battery manufacturing line to adapt it to the future situation where it is required to achieve a reduction of 63 seconds of the current cycle time. For this, a rebalancing process of the presented GALBP problem will be performed, where specific heuristics will be used for its resolution. Once the rebalancing process of the line is finished, a simulation of this new situation will be performed using JaamSim software, this will allow, on the one hand, to verify that a correct rebalancing process has been performed, and on the other hand, to analyse this new situation and to propose improvements for the bottleneck stations. Finally, these improvements will be introduced in the simulation model to assist on the decision making process of deciding which improvement proposal is the most appropriate one.

This study is conducted at Scania, a globally leading company that manufactures trucks and delivers transport solutions to customers around the globe. In this study, the end flow of the chassi manufacturing was mapped in order to identify and eliminate wastes and bottlenecks, with the help of lean principles and discrete event simulation (DES) software. The assembly line consists of a make-to-order production head line that sends out semi-finished trucks to the end flow. The end flow is thereby codependent on the output from the head line. A synchronized tacted flow would minimize the wait in the stations, which is considered a waste in production, and enhance quality of work as deviations become more visible. The complexity of the production system has however made the department disregard the usage and implementation of simulations tools for improvement and decision making. The aim of this study was to evaluate the applicability and feasibility of DES as a tool for waste elimination, to increase throughput in a complex system and for investigating a better ratio between the takt times of the codependent assembly lines. This was done by developing future scenarios with different configurations of the model, studying how the parameters' behavior change in DES. Recommendations for reaching more effective codependent assembly lines with the help of DES were developed, analyzing the benefits and challenges of using simulation solutions for future decision making. The study offered useful insights and practical guidelines for companies with complex codependent assembly lines, wanting to use DES to implement lean principles. Five different improvement scenarios were tested and it was concluded that an increased number of buffer spots would have the largest impact on the throughput. An optimized takt time for a maximized throughput was also possible to identify with an enumeration method with scenarios. The drawback of DES for complex codependent lines was found to be the inability to consider all surrounding factors such as safety, ergonomics, quality and communication, which makes it a less applicable tool for waste elimination. The benefit of the DES simulation was the ability to manage complexities such as; different takt times between lines; gaps that occur in the production because of trucks removed from the head line; the interplay of the various inflows merging; the additional time to receive trucks from the reparation department; and stop times that cause waiting time at the production line. It was therefore considered an applicable tool for deciding the takt time for codependent lines. Denna studie är genomförd på Scania, ett globalt ledande företag som tillverkar lastbilar och levererar transportlösningar till kunder runt om i världen. I denna studie kartlades slutflödet av chassitillverkningen för att identifiera och eliminera slöserier och flaskhalsar, med hjälp av leanprinciper och Discrete Event Simulation (DES). Produktionslinan består av en make-to-order huvudlina som skickar ut halvfärdiga lastbilar till slutflödet. Slutflödet är därmed beroende av utflödet från huvudlinan. Ett mer synkroniserat taktat flöde skulle minimera väntetider på stationerna, vilket anses vara slöseri i produktionen, och förbättra kvaliteten på produkterna. Produktionssystemets komplexitet har dock fått avdelningen att bortse från användningen och implementeringen av simuleringsverktyg för beslutsfattande. Målet med denna studie var att utvärdera användbarheten och genomförbarheten av DES som ett verktyg för att eliminera slöserier för att öka antal producerade produkter i ett komplext system, för att undersöka en bättre relation mellan takttider för olika linor. Detta gjordes genom att utveckla framtidsscenarier med olika konfigurationer av modellen där olika parametrarnas beteende och förändring studerades. Rekommendationer för att nå mer effektiva samberoende monteringslinjer med hjälp av DES utvecklades, där fördelarna och utmaningarna med att använda simuleringslösningar för framtida beslutsfattande analyserades. Studien gav insikter och praktiska förslag för företag med komplexa samberoende monteringslinjer, som vill använda DES för att implementera lean-principer. Fem olika förbättringsscenarier testades och resultatet visade att ett ökat antal buffertplatser skulle ha störst påverkan på antal producerade produkter. En optimerad takttid för att maximera antal producerade bilar var också möjlig att identifiera med en numerisk analys där olika intervall av takttider testats i olika scenarier. Nackdelen med DES för komplexa produktionsflöden visade sig vara oförmågan att ta hänsyn till olika omgivande faktorer som säkerhet, ergonomi, kvalitet och kommunikation. Detta gör det till ett mindre användbart verktyg för att mäta effekten av att eliminera slöserier. Fördelen med DES-simuleringen var förmågan att hantera komplexitet såsom; olika takttider mellan olika flöden; luckor som uppstår i produktionen på grund av borttagna lastbilar från huvudlinjen; samspelet mellan de olika inflödena som slås samman; den extra tiden för att ta emot lastbilar från andra avdelningar; och stopptider som orsakar väntetid vid produktionslinjen. Därmed ansågs DES vara ett användbart verktyg för att bestämma takttiden för komplexa flöden.

This study presents a methodology for synthesizing optimal control algorithms for the flow parameters of a conveyor-type transport system with a variable transport delay. A multi-section transport conveyor is a complex dynamic system with a variable transport delay. The transport conveyor is an important element of the production system, used to synchronize technological operations and move material. The Analytical PiKh-model of the conveyor section was used as a model for designing a control system for flow parameters. The characteristic dimensionless parameters of the conveyor section are introduced and the similarity criteria for the conveyor sections are determined. The model of a conveyor section in a dimensionless form is used to develop a methodology for synthesizing algorithms for optimal control of the flow parameters of a transport conveyor section. The dependencies between the value of the input and output material flow of the section are determined, taking into account the initial distribution of the material along the conveyor section, variable transport delay, restrictions on the specific density of the material, and restrictions on the speed of the belt. The dependencies between the value of the input and output material flow for the case of a constant transport delay are analyzed. A technique for synthesizing algorithms for optimal belt speed control based on the PiKh-model of a conveyor section is presented. As a simplification, a two-stage belt speed control is considered. Particular attention is paid to the methodology for synthesizing optimal control algorithms based on the energy management methodology (TOU-Tariffs). The criteria of control quality are introduced and problems of optimal control of flow parameters of the transport system are formulated. Taking into account differential connections and restrictions on phase variables and admissible controls, which are typical for the conveyor section, the Pontryagin function and the adjoint system of equations are written. As examples demonstrating the design of optimal control, algorithms for optimal control of the flow parameters of the transport system are synthesized and analysis of optimal controls is performed. Дане дослідження презентує методику синтезу алгоритмів оптимального керування потоковими параметрами транспортної системи конвеєрного типу із змінною транспортною затримкою. Багатосекційний транспортний конвеєр – це складна динамічна система із змінною транспортною затримкою. Транспортний конвеєр є важливим елементом виробничої системи, що використовується для синхронізації технологічних операцій та переміщення матеріалу. Як модель для проектування системи управління потоковими параметрами використана аналітична PiKh-модель секції конвеєра. Введено характерні безрозмірні параметри секції конвеєра та визначено критерії подібності до секцій конвеєра. Модель секції конвеєра у безрозмірному вигляді використана для розробки методики синтезу алгоритмів оптимального керування потоковими параметрами секції транспортного конвеєра. Визначено залежності між значенням вхідного та вихідного потоку матеріалу секції з урахуванням початкового розподілу матеріалу вздовж секції конвеєра, змінної транспортної затримки, обмежень на питому щільність матеріалу та обмежень на швидкість стрічки. Проаналізовано залежність між значенням вхідного та вихідного потоку матеріалу для випадку постійної транспортної затримки. Представлено методику синтезу алгоритмів оптимального управління швидкістю стрічки, засновану на PiKh-моделі секції конвеєра. Як спрощення розглянуто двоступінчасте регулювання швидкості стрічки. Особливу увагу приділено методиці синтезу алгоритмів оптимального управління, що ґрунтується на методології енергоменеджменту (TOU-Tariffs). Введено критерії якості керування та сформульовано завдання оптимального керування потоковими параметрами транспортної системи. З урахуванням диференціальних зв'язків та обмежень на фазові змінні та допустимі керування, характерні для конвеєрної ділянки, записана функція Понтрягіна та приєднана система рівнянь. Як приклади, що демонструють проектування оптимального керування, синтезовано алгоритми оптимального керування потоковими параметрами транспортної системи та проведено аналіз оптимальних керування.

The article presents a method for analytical recording of the structure of production lines. A method for specifying a coordinate system is presented on the example of two sequentially installed machines. An abbreviated form of recording the initial coordinate system is proposed. The method of vector solution of transient processes during technological operations is presented. The proposed method for formalizing the technological process of production lines allows for structural analysis of flows by functional characteristics. Представлен метод аналитической записи структуры поточных линий. Представлен способ задания системы координат на примере двух последовательно установленных станков. Предложена сокращенная форма записи исходной системы координат. Представлен метод векторного решения переходных процессов при выполнении технологических операций. Предложенный метод формализации технологического процесса поточных линий позволяет проводить структурный анализ потоков по функциональным признакам.

Purpose Additive manufacturing (AM) offers potential solutions when conventional manufacturing reaches its technological limits. These include a high degree of design freedom, lightweight design, functional integration and rapid prototyping. In this paper, the authors show how AM can be implemented not only for prototyping but also production using different optimization approaches in design including topology optimization, support optimization and selection of part orientation and part consolidation. This paper aims to present how AM can reduce the production cost of complex components such as jet engine air manifold by optimizing the design. This case study also identifies a detailed feasibility analysis of the cost model for an air manifold of an Airbus jet engine using various strategies, such as computer numerical control machining, printing with standard support structures and support optimization. Design/methodology/approach Parameters that affect the production price of the air manifold such as machining, printing (process), feedstock, labor and post-processing costs were calculated and compared to find the best manufacturing strategy. Findings Results showed that AM can solve a range of problems and improve production by customization, rapid prototyping and geometrical freedom. This case study showed that 49%–58% of the cost is related to pre- and post-processing when using laser-based powder bed fusion to produce the air manifold. However, the cost of pre- and post-processing when using machining is 32%–35% of the total production costs. The results of this research can assist successful enterprises, such as aerospace, automotive and medical, in successfully turning toward AM technology. Originality/value Important factors such as validity, feasibility and limitations, pre-processing and monitoring, are discussed to show how a process chain can be controlled and run efficiently. Reproducibility of the process chain is debated to ensure the quality of mass production lines. Post-processing and qualification of the AM parts are also discussed to show how to satisfy the demands on standards (for surface quality and dimensional accuracy), safety, quality and certification. The original contribution of this paper is identifying the main production costs of complex components using both conventional and AM.

In recent years, deep learning and object detection has continuously attracted more attention. Especially in the automotive world where many car manufacturers are currently investigating its possible applications. On production lines, even if processes are more and more automatized mistakes can happen and hinder the performance of an industrial plant. In this study, a method and application of object detection-based deep learning algorithm to detect open flaps on cars, like doors, trunk, hood etc. is examined. With this approach, the advantages of gap detection in cars on production lines, specifically the application of Resnet50 Convolutional Neural Networks (CNNs) and transfer learning in an industrial use case, are demonstrated. We show how the problem of detecting open flaps on cars is modeled in a way that a CNN can be applied to this new kind of application and present a detailed evaluation of the results and challenges. Finally, many suggestions are given for future applications of similar algorithms.

В статье рассматривается метод расчета продолжительности производственного цикла изготовления партии деталей. Производственный цикл изготовления партии деталей является одной из основных характеристик производственной системы, используется для расчета важных показателей планирования производственной деятельности предприятия. Для вывода уравнения движения предметов труда по технологическим операциям использована дискретно-событийная модель производственного процесса. Рассмотрена структура времени обработки предмета труда на технологической операции. Показан источник изменения величины межоперационных заделов на каждой технологической операции. Проанализирована взаимосвязь траекторий движения предыдущего и последующего предметов труда. Записано уравнение движения предмета труда по технологическим операциям с учетом межоперационных заделов и предложены методы его решения. Рассмотрены условия применимости полученных результатов. Проведен анализ затрат машинного времени, необходимого для расчета продолжительности производственного цикла изготовления партии продукции для предприятий полупроводниковой промышленности. Определены перспективы исследований. В статье рассматривается метод расчета продолжительности производственного цикла изготовления партии деталей. Производственный цикл изготовления партии деталей является одной из основных характеристик производственной системы, используется для расчета важных показателей планирования производственной деятельности предприятия. В настоящее время задача расчета продолжительности производственного цикла для несинхронизированных поточных линий остается актуальной. Рассмотрены условия применимости полученных результатов. Проведен анализ затрат машинного времени, необходимого для расчета продолжительности производственного цикла изготовления партии продукции для предприятий полупроводниковой промышленности. Определены перспективы исследований. The method of calculating the duration of the production cycle for manufacturing a batch of parts is considered. The production cycle of manufacturing the batch of parts is one of the main characteristics of the production system. It is used to calculate the important indicators of planning the production activity of the factory. At present, the task of calculating the duration of the production cycle for unsynchronized production lines remains relevant. The task takes on a special relevance in the case when the processing time of a work item in a technological operation is a random quantity. The present work is devoted to the analysis of this case. To derive the equation of motion of labor objects for technological operations, a discrete-event model of the production process is used. The structure of the processing time of an object of labor on a technological operation is considered. The source of change in the value of interoperational stocks at each technological operation is shown. The interrelation of the trajectories of the previous and after subjects of labor is analyzed. The equation of motion of an subject of labor on technological operations is recorded, taking into account the interoperational stocks. Methods for its solution are proposed. Conditions for the applicability of the obtained results are considered. The analysis of the machine time spent for calculating the duration of the production cycle of manufacturing the batch of products for the factory of the semiconductor industry was carried out. Prospects for research have been determined.

Industries that are in transition to Industry 4.0 often face challenges in applying data-driven methods to improve performance. While ample methods are available in literature, knowledge on how to select and apply them is scarce. This study aims to address this gap reported on the design and implementation of data-driven models for predictive maintenance at TATA Steel, Shotton. The objective of the project is to predict the wearing behaviour of the components in the steel production line for maintenance activity decision support. To achieve the predictive maintenance goal, the approach applied can be summarized as follows: 1. business understanding and data collection, 2. literature review, 3. data preparation and exploration, 4. modelling and result analysis and 5. conclusion and recommendation. The data-driven methods that were analysed and compared are: Partial Least Squares Regression (PLSR), Artificial Neu- ral Network (ANN) and Random Forest(RF). After cleaning and analysing the production line data, predictive maintenance with the current available data in TATA Steel, Shotton is best feasible with PLSR. The study further concludes that, predictive maintenance is likely to be feasible in similar industries that are in transition to industry 4.0 and have growing volumes of production data with varying quality and detail. However, as illustrated in this case study, careful understanding of the industrial process, thorough modeling and cleaning of the data as well as careful method selection and tuning are required. Moreover, the resulting model needs to be packaged in a user friendly way to find its way to the job floor.

Most factory production processes are completed by machines and workers on production lines. The operation schedule is arranged to reduce the cost of the enterprises to obtain the maximum economic profit for sustainable running. Previous studies usually investigated the working time while only considering the workers’ conditions. This study proposed a method to optimize the operation schedule by jointly considering the workers’ fatigue states and the operation states of machines. This method was proposed based on a system structure called the multistate consecutively connected system (MCCS), which has been widely applied in many areas, such as electronic communications. This structure is also an analogy of the production line. The corresponding model is constructed based on the universal generating function (UGF) since it is a powerful tool in modeling a consecutively connected system. The proposed model can be used to evaluate the different productivities of different types of workers in different states and to realize the screening of the whole scheme through simulation. According to the proposed method, we obtained the optimal operation schedule, including the working time, rest time and allocation strategy for a production line system. Some examples are provided to illustrate the proposed method.

With the advent of modern communication and control strategies, existing industrial enterprises are now being transformed as per Industrial Revolution (IR) 4.0 standards to maximize production rates and monetary gains. To cope with the pace of the modern technological revolution, the Government of Saudi Arabia has launched “Vision 2030”. This research article presents the full automation process of an existing production line at the College of Engineering, King Saud University, as per “Vision 2030” guidelines. Initially, a production line was designed to produce flavored yogurt bottles from a user-defined flavor and plain yogurt mixture. The research project was completed in two phases. During phase I, smart sensing, control, and automation equipment were used to minimize human intervention, the so-called semi-automated mode of operation. A bottle-feeding mechanism and robotic arms were later integrated to eliminate human intervention during the second phase. Moreover, during phase II, Node-RED, Telegram Bots, and a Raspberry Pi 4 controller were used to achieve IoT-based monitoring and control as per Industry 4.0 requirements. A comparative performance analysis was conducted between semi-automated and fully automated modes of operation to demonstrate the benefits of the fully automated operational mode. The performance of the fully automated system was found to be superior in comparison with the semi-automated system.

In recent years, 3D vision robot picking has been widely used in the fields of manufacturing, logistics, and warehouse due to its flexibility in handling various models. In this paper, we propose a robust and precise 3D vision guided robot picking method using multi-channel image information fusion. The major challenges are the failure or inaccurate of object localization and pose estimation caused by environment. Various considerations, we utilize a 3D camera based on binocular structed light to obtain the high accuracy RGB-D image with an additional customized illumination unit. In addition, we introduce the fusion method using multi-exposure control and multi-channel model from multi-color images to establish the reliable model matching for all conditions. Our system calculates the location and pose of the stove according to the rectangular template and the normal vector of the bottom surface to realize visual guidance. By projecting the point cloud onto the stove plane, only the height information is retained to generate a pseudo-image. Our 3D vision system reaches ≥99.8% successful pickup rate with the ±2mm accuracy along X, Y, and Z directions and±0.2°rotational accuracy along RX, RY, and RZ for both bare and painted surfaces under various illumination conditions during production. Our stove-picking systems installed in the welding and assembly stations improve the flexibility and the efficiency of the stove production line (100,000 unit/year).

This research focused on the development of a Digital Model (DM) of a production line at a medical device company, with the objective of providing decision support to stakeholders based on their energy consumption. This model aims to reduce energy consumption by bringing operational data to process engineers, allowing them to make efficient improvement decisions while in production. In order to achieve this objective, the twin transition of digital integration and energy efficiency was enacted by organisations such as the International Energy Agency (IEA). This two-pronged approach involved working with process owners to understand the decision-making process that they undertook to streamline performance and develop the means to digitalise this data while also working with facilities and maintenance engineers to understand which equipment played the most important roles in the production process from an energy consumption perspective. By bringing the process data and energy data together in a digital model of the process, a decision support system could be developed which would unlock the potential to streamline operations not just from an output perspective, but also from an energy efficient perspective. When examining the process step with data catagorised as energy, operational and maintenance, it was found that only operational data was sufficient to support digital modelling in its current state. Therefore, the installation of a wireless energy metering network would be required to support digital modelling and further digital integration.

Quality control has long been one of the most challenging fields of manufacturing. The development of advanced sensors and the easier collection of high amounts of data designate the machine learning techniques as a timely natural step forward to leverage quality decision support and manufacturing challenges. This paper introduces an original dataset provided by the automotive supplier company VALEO, coming from a production line, and hosted by the Ecole Normale Superieure (ENS) Data Challenge to predict defects using non-anonymised features, without access to final test results, to validate the part status (defective or not). We propose in this paper a complete workflow from data exploration to the modelling phase while addressing at each stage challenges and techniques to solve them, as a benchmark reference. The proposed workflow is validated in series of experiments that demonstrate the benefits, challenges and impact of data science adoption in manufacturing.

In this paper, based on the experimental investigations of the cold forming line of the sheet metal using rollers, the deformations of the supporting frame of the machining module were analyzed. After that, a comparison of experimental and modeled values was performed. Experimental studies have included the measurement of deformation of the frame in the cold rolling process on a single machining module. The following resources were used to perform the experiment: a cold forming profile line, three types of sheet metal of different thicknesses, widths and mechanical characteristics, measuring straps for measuring frame deformation, signal amplifiers and two computers with appropriate programs.The goal of the paper is to develop a mathematical model to obtain a model which can be used for analysis of deformation of the supporting frames of the processing modules. The resulting mathematical model could be important for engineers to develop new production lines for cold forming sheet metal using rollers.

In manufacturing firms, there are many factors that can affect product completion time in production lines. However, in a real production environment, such factors are uncertain and increase the adverse effects on product completion time. This research focuses on the role of internal factors in small- and medium-scale supply chains in developing countries, enhancing product completion time during the manufacturing process in fuzzy conditions. In the first step of this research, a list of factors was found clustered into six main groups: technology, human resources, machinery, material, facility design, and social factors. In the next step, fuzzy weights of each group factor were determined by a fuzzy inference system to reflect the uncertainty of the factors in utilizing product completion time. Then, a hybrid fuzzy–TOPSIS-based heuristic is proposed to generate and select the best production alternative. The outcomes showed that the proposed method could generate and select the alternative with a 10.13% lower product completion time. The findings also indicated that using the proposed fuzzy method will cause less minimum variance compared to the crisp mode.

Publisher Copyright: © 2021 IEEE. Digital Twins are increasingly being introduced for smart manufacturing systems to improve the efficiency of the main disciplines of such systems. Formal techniques, such as graphs, are a common way of describing Digital Twin models, allowing broad types of tools to provide Digital Twin based services such as fault detection in production lines. Obtaining correct and complete formal Digital Twins of physical systems can be a complicated and time consuming process, particularly for manufacturing systems with plenty of physical objects and the associated manufacturing processes. Automatic generation of Digital Twins is an emerging research field and can reduce time and costs. In this paper, we focus on the generation of Digital Twins for flexible manufacturing systems with Automated Guided Vehicles (AGVs) on the factory floor. In particular, we propose an architectural framework and the associated design choices and software development tools that facilitate automatic generation of Digital Twins for AGVs. Specifically, the scope of the generated digital twins is controlling AGVs in the factory floor. To this end, we focus on different control levels of AGVs and utilize graph theory to generate the graph-based Digital Twin of the factory floor.

Industry 4.0 has been a hot topic in recent years. The process of integrating Cyber-Physical Systems (CPS), Artificial Intelligence (AI), and Internet of Things (IoT) technology, will become the trend in future construction of smart factories. In the past, smart factories were developed around the concept of the Flexible Manufacturing System (FMS). Most parts of the quality management process still needed to be implemented by Automated Optical Inspection (AOI) methods which required human resources and time to perform second stage testing. Screening standards also resulted in the elimination of about 30% of the products. In this study, we sort and analyze several Region-based Convolutional Neural Network (R-CNN) and YOLO models that are currently more advanced and widely used, analyze the methods and development problems of the various models, and propose a suitable real-time image recognition model and architecture suitable for Integrated Circuit Board (ICB) in manufacturing process. The goal of the first stage of this study is to collect and use different types of ICBs as model training data sets, and establish a preliminary image recognition model that can classify and predict different types of ICBs based on different feature points. The second stage explores image augmentation fusion and optimization methods. The data augmentation method used in this study can reach an average accuracy of 96.53%. In the final stage, there is discussion of the applicability of the model to detect and recognize the ICB directionality in

This paper studies workforce assignment problem for battery production in a company in Turkey. Several types of batteries are produced in the studied company. Mostly, the operations are semi-automated. In the production process, the workers are assigned to multiple operations irregularly based on the priority of productions. In the company, average utilization of worker is low, and average cycle time of a product is high due to inefficient allocation of the workforce within the operations. In order to analyze the main system problem, we simulate the system and observe the queue lengths to identify the bottlenecks. By dynamic assignment of workers at stations based on real time queue conditions, the workloads can be balanced throughout the production lines. In this project, a simulation-based system improvement is completed by applying: (i) dynamic utilization of workforce to reduce average cycle time of a battery, (ii) assignment of parallel workforce where they can work for the same operation simultaneously, and (iii) observation of real-time queue lengths of stations. Three dynamic assignment policies are developed and compared with each other. The best policy providing minimum cycle time for a battery production is selected to be the best.

In large-scale manufacturing and assembly applications, especially when trying to automate most steps, implementing quality control as early in the process as possible is the key to prevent expenses later. We deal mainly with the production of DC motor powered fuel pumps, which are commonly used in the automotive industry. The goal of this paper is to present a newly developed technique for non-invasive fault detection of a DC motor’s direction of rotation using a stray magnetic field out of the motor chassis. The results presented in this paper show that it is possible to detect faults even on low-power motors while the algorithm is kept as simple as possible to allow for large-scale deployment on a production line. It also gives new insight into the behavior of the stray magnetic field of electric motors, which may benefit other applications and future research.

Attacks on industrial control systems (ICS) have been intensively studied during the last decade. Malicious alternations of ICS can appear in several different ways, e.g. in changed network traffic patterns or in modified data stored on ICS components. While several heuristics and machine learning methods have been proposed to analyze different types of ICS data regarding anomalies, no work is known that uses the data of Totally Integrated Automation (TIA) Portal for anomaly detection. TIA Portal is a popular software system for organizing the ICS, with which configuration and programming data can be viewed, changed and deleted. By saving the single project datasets historically, old versions of the current system configurations can be restored. In this initial work, we propose heuristics that detect anomalies in the TIA Portal data. In particular do we analyze the historical modifications within TIA Portal data by investigating long-term backups. Our approach covers both, changes to the data caused by infiltrated attacks as well as malicious changes made by employees who have direct access to the machines. We therefore started to examine real TIA Portal project data of an automotive manufacturer’s production line, covering a period of about three years of historical data, for various features that may indicate anomalies.

Optical metrology is a key element for many areas of modern production. Preferably, measurements should take place within the production line (in-process) and keep pace with production speed, even if the parts have a complex geometry or are difficult to access. The challenge for modern optical in-process measurements is, therefore, how to simultaneously make optical metrology precise, fast, robust and capable of handling geometrical complexity. The potential of individual techniques to achieve these demands can be visualized by the tetrahedron of optical metrology. Depending on the application, techniques based on interferometry or geometrical optics may have to be preferred. The paper emphasizes complexity and robustness as prime areas of improvement. Concerning interferometric techniques, we report on fast acquisition as used in holography, tailoring of coherence properties and use of Multiple simultaneous Viewing direction holography (MultiView), self reference used in Computational Shear Interferometry (CoSI) and the simultaneous use of several light sources in Multiple Aperture Shear Interferometry (MArS) based on CoSI as these techniques have proven to be particularly effective. The use of advanced approaches based on CoSI requires a transition of the description of light from the use of the well-known wave field to the coherence function of light. Techniques based on geometric optics are generally comparatively robust against environmental disturbances, and Fringe Projection (FP) is shown to be especially useful in very demanding measurement conditions.

Quality control is a key process designed to ensure that only products satisfying the defined quality requirements reach the end consumer or the next step in a production line. In the food industry, in the packaging step, there are many products that are still evaluated by human operators. To automate the process and improve efficiency and effectiveness, computer vision and artificial intelligence techniques can be applied. This automation is challenging since specific strategies designed according to the application scenario are required. Focusing on the quality control of the sealing and closure of matrix-shaped thermoforming food packages, the aim of the article is to propose a deep-learning-based solution designed to automatically perform the quality control while satisfying production cadence and ensuring 100% inline inspection of the products. Particularly, the designed computer vision system and the image-based criteria defined to determine when a product has to be accepted or rejected are presented. In addition, the vision control software is described with special emphasis on the different convolutional neural network (CNN) architectures that have been considered (ResNet18, ResNet50, Vgg19 and DenseNet161, non-pre-trained and pre-trained on ImageNet) and on the specifically designed dataset. To test the solution, different experiments are carried out in the laboratory and also in a real scenario, concluding that the proposed CNN-based approach improves the efficiency and security of the quality control process. Optimal results are obtained with the pre-trained DenseNet161, achieving false positive rates that range from 0.03 to 0.30% and false negative rates that range from 0 to 0.07%, with a rejection rate between 0.64 and 5.09% of production, and being able to detect at least 99.93% of the sealing defects that occur in any production. The modular design of our solution as well as the provided description allow it to adapt to similar scenarios and to new deep-learning models to prevent the arrival of faulty products to end consumers by removing them from the automated production line Tis work has been carried out as part of the Industrial Doctoral program from the Catalan Government (2018– 2021, Ref. 2018 DI 026). It has also been supported by grants from the Catalan Government (Nr. 2017-SGR-1101) and from the Spanish Government (Nr. MICIU PID 2019-106426 RB-C31)

This paper presents a case study of continuous productivity improvement of an automotive parts production line using Internet of Everything (IoE) data for fault monitoring. Continuous productivity improvement denotes an iterative process of analyzing and updating the production line configuration for productivity improvement based on measured data. Analysis for continuous improvement of a production system requires a set of data (machine uptime, downtime, cycle-time) that are not typically monitored by a conventional fault monitoring system. Although productivity improvement is a critical aspect for a manufacturing site, not many production systems are equipped with a dedicated data recording system towards continuous improvement. In this paper, we study the problem of how to derive the dataset required for continuous improvement from the measurement by a conventional fault monitoring system. In particular, we provide a case study of an automotive parts production line. Based on the data measured by the existing fault monitoring system, we model the production system and derive the dataset required for continuous improvement. Our approach provides the expected amount of improvement to operation managers in a numerical manner to help them make a decision on whether they should modify the line configuration or not.