IFIP Open Access Digital Library
Not a member yet
22614 research outputs found
Sort by
An AUGMECON2VIKOR Algorithm for a Multi-objective Model in a Sustainable Manufacturing System Under Reliable Constraints
No full textInternational audienceRecognizing suitable manufacturing methods for goods can be taken into account as a crucial manufacturing task resulting in the optimization of activities. It has gained significance in the food industry owing to the distinct limitations and assumptions posed by perishable as well as non-perishable goods in this issue. Therefore, this research presents a novel mathematical formulation based on knowledge discovery and an assignment model for the optimization of manufacturing systems for perishable as well as non-perishable tailored to satisfy their unique features. In the proposed formulation, three objectives of minimizing the makespan, the production costs, and the energy consumption are considered. Two numerical examples considering both small and medium sizes are applied to appraise the performance of the combination of an improved version of epsilon-constraint augmented (AUGMECON2) and VlseKriterijumska Optimizacija I Kompromisno Resenje in Serbia (VIKOR), namely AUGMECON2VIKOR. The sensitivity analysis represents the positive reliable constraint impacts, influencing objective functions
Development of Automated Negotiation Models for Suppliers Using Reinforcement Learning
No full textPart 6: Applications of Artificial Intelligence in ManufacturingInternational audienceDuring a negotiating process in the supply chain, the negotiating parties try to maximize their interests while presenting a reasonable proposal that the counterpart may accept. Human negotiators, however, can have difficulties in making the optimal negotiation proposal or decision due to various limitations related to time, cost, and information processing capabilities. To deal with these issues, this study proposes artificial intelligence-based models to automate the negotiation process for a supplier in the supply chain. Specifically, we focus on the sell-side perspective as this area has not been studied comprehensively. To deal with the insufficient amount of data, we generate data on quantity (Q), price (P), and delivery lead time (D) by analyzing the correlation among these three variables from the available real transaction data. Then, more than 23,000 negotiation episodes between a buyer and a seller are simulated with correlated Q, P, and D. For learning the optimal negotiating strategy through simulated episodes, we apply the reinforcement learning models based on the Q-learning algorithm. We present two negotiation models: (i) a P negotiation model dependent on Q and (ii) a P negotiation model dependent on D. Our results show that the proposed structure of the automated negotiation model with correlated Q, P, and D can be applied to various negotiation environments by helping sell-side agents
Vibration-Based Operating Status Monitoring of a Production Line with Low-Cost IoT Devices
No full textPart 6: Applications of Artificial Intelligence in ManufacturingInternational audienceMany production lines still in use today have been designed without provisions or machine interfaces for data recording and data analysis. An efficient solution for generating operation metrics for these brownfield lines is smart retrofitting with Internet of Things (IoT) devices. We present a cost-efficient, nonintrusive IoT solution for monitoring the operating status of modules of an assembly line based on the measured background vibrations. In contrast to existing solutions which often examine a single machine or process step, our solution monitors entire production modules with many moving components on a higher, business-focused level. The vibration is measured by a wireless network of low-cost IoT devices. A middleware software processes the sensor data for later analysis with unsupervised machine learning. Experiments at an assembly line have proven that low-cost IoT solutions are capable of identifying normal operation, state transitions, and standstill of production modules from the background vibrations. The monitoring of the actual operating status is necessary for deriving key indicators for business questions or maintenance optimization
An Introduction to Machine Learning Lifecycle Ontology and Its Applications
No full textPart 5: Open Knowledge Networks for Smart ManufacturingInternational audienceMachine Learning (ML) adoption is on the rapid rise, with a nearly 40% compound annual growth rate over the next decade. In other words, companies will be flooded with ML models developed with different datasets and software. The ability to have information at one’s fingertips about how these ML models were developed, what they were used for, what their performances and uncertainties are, what their internal structure looks like, and what datasets were used can have several benefits. These pieces of ML metadata are what we collectively call ML lifecycle information. This paper explains our current research into developing an ML Lifecycle Ontology (MLLO) to capture such information in a knowledge graph. The main objective of this paper is to describe the motivation through use cases and show that future research is warranted. To that end, basic and advanced use scenarios are described. MLLO is then introduced at a high level and validated with the basic use case to show its value. We then describe future work we are undergoing to demonstrate the hypotheses in the advanced use case in which MLLO not only serves as a standard queryable representation of ML metadata across different ML software but also as a connector to domain knowledge to assist in the ML model development and reuse
Dynamic Multi-objective Opti-State Decision-Making Method for Intermittent Synchronized Production Operation System
No full textPart 7: IntralogisticsInternational audienceIn the era of escalating customer demands for tailored products, advancements in intelligent manufacturing technologies and the proliferation of diverse production and operational models, production-logistics systems face heightened internal and external disruptions. This work contributes a novel dynamic multi-objective opti-state decision-making framework and method to address the complex decision-making challenges that arise from such disruptions. It delves into the re-decision-making requirements for maintaining optimal state performance in production-logistics systems amidst disturbances, focusing on operational objectives. The proposed method employs intelligent algorithms for local sub-models, utilizing the gray target theory to determine the best dynamic multi-objective optimization strategy. To demonstrate its practicality, the method is instantiated as an intermittent synchronized production operation system, with a case study in the context of enterprises with intermittent production, validating the effectiveness of the proposed approach
Construction of a Demonstrator for Artificial Intelligence-Supported, Automated Dismantling of Battery Systems
No full textPart 1: Smart Manufacturing Assets as Drivers for the Twin Transition Towards Green and Digital BusinessInternational audienceIn the context of increasing environmental concerns and the push towards sustainable practices, the recycling and repurposing of battery systems have become imperative. This paper presents a concept for the automated disassembly of battery systems from pack to module using artificial intelligence. The focus is on the design and process sequence of two independently designed systems. One system is responsible for the separation and screwing processes within the dismantling of battery systems, while the other system handles the removal of corresponding battery components. The generation of data for linking artificial intelligence with dismantling systems and networking using digital twins is a topic that requires investigation and practical implementation through several experiments in the future
Integrating Machine and Quality Data for Predictive Maintenance in Manufacturing System
No full textPart 2: Engineering and Managing AI for Advances in Asset Lifecycle and Maintenance ManagementInternational audienceMaintenance and quality control are typically disjoint areas in a production system and even though interactions between them do exist, they are limited. In some cases, the quality deviations are reported directly by the client the product is sold to before maintenance actions are taken to repair the faulty machines and prevent these specific deviations. In this paper, we claim that by using machine and quality data in combination, it is possible to generate information about the process and the resulting product, that will allow to detect deviations in earlier stages, likely before the product reaches the client, possibly even before it is produced. We analyze a production process over a period of two years, during which operational parameters of the machines executing the process are reported, as well as the quality deviations of the parts produced. The data gathered is used to establish whether there exists a correlation between the machine status and the quality deviations of the products. Experiments show that the correlation increases when adjustments to the machines are made. This evidence supports our hypothesis of the possibility of using quality and machine data in combination in the development of future predictive maintenance solutions
Key Factors for Sustainability along the Lifecycle of Smart Product Service Systems
No full textPart 1: Smart Manufacturing Assets as Drivers for the Twin Transition Towards Green and Digital BusinessInternational audienceThis paper applies an explorative literature review to analyze the generalizability of the lifecycle of industrial smart Product-Service Systems (PSS), comprising both capital goods and associated services. It investigates the factors influencing sustainability throughout this lifecycle, considering the complexities inherent in such systems. The article discusses whether assessing the sustainability of services versus goods within the PSS framework requires distinct criteria. By analyzing existing lifecycle models and indicator frameworks, the research identifies key dimensions and criteria essential for describing and evaluating economic and environmental sustainability across the lifecycle. Key questions addressed include the identification of dimensions and criteria crucial for sustainability assessment, considering the complexities and uncertainties inherent in the lifecycle of capital goods. The findings provide a first step towards a framework for measuring and improving sustainability within our context. To better understand the dynamics and uncertainties along the lifecycle, enhanced collaboration between the involved domains is recommended. This could be realized through industrial case studies and comprehensive impact assessments
Asset Lifecycle Management and Digital Servitization: A Case Study in Machining
No full textPart 4: Methods and Tools to Achieve the Digital and Sustainable Servitization of Manufacturing CompaniesInternational audienceDigital servitization is increasingly relevant for competitiveness and long-term sustainability in several industrial sectors. Firms with capital assets and long lifespans have been documented as promising candidates for maximizing the value of resource-efficient operations and lifecycle extension opportunities. This paper investigates the conceptual overlap of asset lifecycle management and digital servitization in the context of machining in industry to maximize resource efficiency and lifecycle extension. While existing literature primarily focuses on early-stage strategic planning, this study emphasizes the significance of decision-making during the use phase of assets, highlighting the need for a balanced allocation of resources between late-stage decisions and early strategic planning, to capture sustainable value. This study presents a map of strategic options that connect levels of digital servitization and eco-efficiency principles across an asset’s lifecycle. By exemplifying through a case study, the results of this paper include a mapping of scenarios highlighting the importance of integrating digital servitization and asset lifecycle management strategies to achieve improved sustainability in industrial settings
Comparing Digital Twins and Virtual Engineering in Buyer Supplier Relationships for Complex Production Facilities
No full textPart 3: Digital Twin Concepts in Production and ServicesInternational audienceIn today’s highly competitive and interconnected global marketplace, the effective management of buyer-supplier relationships is essential for organizations seeking to stay ahead. With the rise of complex production facilities, ensuring product quality and optimizing communication between buyers and suppliers presents an escalating challenge. This complexity is further compounded by the integration of Digital Twins and Virtual Engineering, requiring innovative solutions to navigate the intricacies of modern supply chain dynamics. This article explores the role of Digital Twins and Virtual Engineering as a strategic approach to enhance buyer-supplier relationship management within the context of complex production facilities using insights from the Principal Agent Theory. Based on a systematic literature review, we explore current approaches to the use of virtual engineering and digital twins to overcome existing tensions from principal-agent theory