A Surrogate Model to Predict Production Performance in Digital Twin based Smart Manufacturing

With the dynamic arrival of production orders and unforeseen changes in shop-floor conditions within a production system, production scheduling presents a challenge for manufacturing firms to ensure production demands are met with high productivity and low operating cost. Before a production schedule is generated to process the incoming production orders, production planning is performed. Given the large number of input parameters involved in production planning, it poses the challenge on how to systematically and accurately predict and evaluate the production performance. Hence, it is important to understand the interactions of the input parameters between production planning and scheduling. This is to ensure that the production planning and scheduling are coordinated and can be performed to achieve the optimal production performance such as minimizing cost effectively and efficiently. Digital twin presents an opportunity to mirror the real-time production status and analyze the input parameters affecting the production performance in smart manufacturing. In this paper, using the capabilities of real-time synchronization of production data in digital twin, we propose an approach to develop a surrogate model to predict the production performance using input parameters from a production plan. Multivariate adaptive regression spline (MARS) is applied to construct the surrogate model based on three categories of input parameters, such as current production system load, machine-based and product-based parameters. The effectiveness of the proposed MARS model is demonstrated using an industrial case study of a wafer fabrication production based on random sampling of varying numbers of training data set.

Prediction of Production Performance in Smart Manufacturing Using Multivariate Adaptive Regression Spline

With the dynamic arrival of production orders and ever-changing shop-floor conditions within a production system, production scheduling presents a challenge for manufacturing firms to ensure production demands that are met with high productivity and low operating cost. Before a production schedule is generated to process the incoming production orders, the production planning stage must take place. Given the large number of input parameters involved in production planning, it is important to understand the interactions of input parameters between production planning and scheduling. This is to ensure that production planning and scheduling could be determined effectively and efficiently in achieving the best or optimal production performance with minimizing cost. In this study, by utilizing the capabilities of data pervasiveness in smart manufacturing setting, we propose an approach to develop a surrogate model to predict the production performance using the input parameters from a production plan. Based on three categories of input parameters, namely current production system load, machine-based and product-based parameters, the prediction is performed by developing a surrogate model using multivariate adaptive regression spline (MARS). The effectiveness of the proposed MARS model is demonstrated using an industrial case study of a wafer fabrication production through the random sampling of varying numbers of training data set.

Dye Schedule Optimization: A Case Study in a Textile Industry

In a demanding and globalized market, production management plays a fundamental role in the company’s reference. Proper management of the production area allows companies to obtain productivity gains, reducing operational costs and make contributions to face the competitiveness of their competitors. When defining its strategic objectives in a productive system, it is necessary to formulate plans to manage human resources and strategies based on requirements. In this context, planning, production, and control (PPC) is an excellent ally of the organizations. The adequate development of the activities of the PPC allows companies to minimize production orders not attended, minimize stocks of raw materials, and finished products, minimize idleness of human resources by efficient allocation of work and minimize production processing times. The present work proposes a study to organize and develop a model that guides the prediction of the setup gain in the fabric dyeing process, structured by the traveling salesman problem.

Professional education in the context of increased demand in the labor market

The issue of the shortage of qualifi ed workers is of relevant importance in the Russian labor market. The modern labor market in the Russian Federation is in dire need of workforce. The market economy places high demands on the quality of the workforce, its professionalism, educational and qualification level. In conditions of fierce competition in the labor market for specialists, jobs at manufacturing enterprises are often unoccupied for various reasons. On the one hand, companies offering vacancies for blue-collar workers cannot find employees with sufficient qualifi cations. On the other hand, people who have received a vocational profession cannot ensure the fulfi llment of important production orders at the proper level, due to the lack of the necessary qualifications. Thirdly, young people prefer to work anywhere, but not in the field they studied. The article is devoted to the key issues of training specialists at the present stage. Research methods include a comprehensive analysis of statistical data and articles on resolving the problem of the workforce shortage, ways to solve the problem of the provision of proper qualification level in vocational specialties, increasing the prestige of vocational professions and motivating young people to work in the field of industrial production. As a result of the analysis carried out in the article, the author concludes that a positive change in this direction can be achieved only under the condition of an integrated approach to the problem and involvement of all interested parties in its solution. Meanwhile, the main emphasis should be placed on early vocational guidance, motivation and incentivization of young people and students, and increasing the prestige of vocational occupations.

Economic model of forecasting financial condition of the enterprise

This article shows the calculation of a the organization of the innovation process as a scientific direction can be considered as a form of scientific knowledge, studying the laws of creation and development of production systems and forming methods of production organization, which provide effective construction and interaction of elements, parts and structure of systems in dynamic conditions of production. Organization of development of new products includes preparation of production of new and modernization of manufactured products, improvement of production technology, current regulation and control of all production units. It covers all stages of production and is systemic in nature, subordinating all private tasks to the main - the maximum satisfaction of social needs through the production of competitive products. In the system plan the organization of innovative activity represents set of forms, methods and receptions of scientifically proved connection of labor force with means of production. This connection is based on the specified goals of the system and the functions of its individual elements. The type of production is defined by the complex characteristic of technical, organizational and economic features of production caused by breadth of the nomenclature, regularity, stability and volume of production. A single production is characterized by a small volume of production of the same products, the re-manufacture and repair of which, as a rule, are not provided. Single and close to it small-scale production is characterized by the manufacture of parts of a large range of jobs that do not have a certain specialization. This production should be sufficiently flexible and adapted to the implementation of various production orders. The sites are equipped with universal equipment and equipment, the operations are used by workers-generalists of high qualification, in many areas practiced combination of professions. Serial production is characterized by the production of a limited range of parts in batches, repeated at regular intervals. This allows the production of new products to use along with universal special equipment.

A simulation-based approach to study the influence of different production flows on manufacturing of customized products

Manufacturing products tailored to the individual requirements of customers is a must if companies want to compete effectively on the market. The production of customized goods poses new challenges for all areas of functioning of production systems. It is necessary to adopt such rules and methods that will allow a flexible response to product design changes and their demand In the organization of production flow (materials and information). The article presents research carried out in the SmartFactory laboratory of the Poznań University of Technology regarding the impact of the structure of products (customization) on the realization of current production orders. The research was carried out using the FlexSim simulation environment. Based on simulation experiments for three forms of organization of production flow with varying degrees of flexibility of production resources, an analysis was made of the time of execution of various sets of production orders and the level of use of available working time. The results of research indicate that in the production of products with low and high planned labor consumption, the use of universal production station is the most advantageous. For such a solution, the degree of utilization of the available working time of production stations is also the highest. It was also found that the principles of scheduling production orders affect the effectiveness of the production system. The best results were obtained for the production schedule, where the sequence of production orders was established from the lowest planned time of resource loading.

The European Commission’s e-Evidence Proposal – Critical Remarks and Proposals for Changes

In response to problems that exist in practice pertaining to how law enforcement authorities in European Union Member States can obtain electronic evidence concerning the commission of a crime, on 17 April 2018 a Proposal for a Regulation of the European Parliament and of the Council on European Production and Preservation Orders for electronic evidence in criminal matters (COM(2018) 225 final, 2018/0108 (cod)) was published. The proposal contains a series of new solutions aimed at speeding up and facilitating cooperation within the EU on obtaining electronic evidence in criminal matters. It is worth examining how the specific solutions accepted and the way they have been formulated may affect the fundamental rights of participants in criminal proceedings, particularly when that impact may be adverse. From this perspective, a detailed analysis is made of what entities will be authorised to issue European Production Orders, in relation to what kinds of electronic evidence, and under what conditions.

Multi-Objective Implementation of Additive Manufacturing in Make-to-Stock Production

As additive manufacturing (AM) develops and matures over the years, it has reached a stage where implementation into a conventional production system becomes possible. With additive manufacturing currently suitable for product personalization/high customization yet small volume production, there are various ways of implementation in a conventional production line. This aim of this paper is to explore the implementation of additive manufacturing in a complementary manner to process internal job orders of large quantities in make-to-stock (MTS) production. Splitting of production orders is allowed and production can be carried out by both injection moulding and additive manufacturing processes simultaneously, with the latter being able to produce various MTS parts in a single build. NSGA-III together with scheduling and rule-based heuristic for allocation of parts on build plate of additive manufacturing process is used to solve the multi-objective implementation problem, with performance measures being cost, scheduling and sustainability. The algorithm will be incorporated with scheduling and rule-based heuristic for allocation of parts on build plate of additive manufacturing process. An experiment using an industry case study is conducted to compare the performance measures with and without implementing additive manufacturing.

Digitalization of Multi-Object Technological Projecting in Terms of Small Batch Production

Decreasing the share of time for the technological training of new product creation is an actual and perspective task. The actuality of the given task always increases with the development of machine-building production. Changes which happen inside the organization of industrial production are connected to the development of consumer demand. Modern tendencies are such that there can be seen a constant lowering of batch products with an increase in the range of their production, and, consequently, a reduction in the production stage of the product life cycle. Under these conditions, it is necessary to react as quickly as possible to changes of external (for example, the arrival of new production orders, adjusting the number of already started production, etc.) and internal conditions (for example, stopping technological equipment for organizational reasons, correcting production routes for parts, etc.). Obviously, the effectiveness of the functioning of the production system will be determined primarily by the right decisions. Errors lead to large material costs and a serious loss of time, which can be fatal for an enterprise. The development goal described in the article is to build a digital model of a production system that allows—on a machine time scale and in the absence of material costs—the analysis of various control scenarios and finding correct solutions in in short time. The methodological basis for constructing such models is the use of simulation modeling with the combination of discrete event and agent modeling. The construction of a model on this principle allows its openness to accumulate information about successful decisions made and use them to solve similar problems in the future. The benefit of this approach is the ability to predict the production situation over time, rational distribution of technological resources, reducing equipment downtime, streamlining the routes of production tasks and determining the stages of acquiring the necessary materials and components. It increases the competitiveness of the enterprise and ensures its economic stability.