Product platforms represent an effective strategy implemented by manufacturers to cope with dynamic market demands, decrease lead-time and delay products differentiation. A decision support system (DSS) for product platforms design and selection in high-variety manufacturing is presented. It applies median-joining phylogenetic networks (MJPN) for the platforms design and phylogenetic tree decomposition for platforms selection by determining the product family phylogenetic network and defines the platforms at various levels of assembly corresponding to different trade-offs between number of platforms (variety) and number of assembly/disassembly tasks (customisation effort). Product platforms are reconfigured and customised to derive final product variants. The phylogenetic tree is decomposed in multiple levels, from the native platforms to the final variants. New Platforms Reconfiguration Index (PRI) and Platforms Customisation Index (PCI) were developed as metrics to evaluate the platforms customisation effort. A case study of a large family of plastic valves is used to demonstrate the DSS application. It shows reduction of 60% in platforms variety and increases in platform customisation assembly/disassembly tasks by only 20% leading to significant production and inventory efficiencies and cost savings. This methodology supports companies in the design and selection of best product platforms for high-variety to reduce cost and delivery time.

Industry 4.0 emerged in the last decade as the fourth industrial revolution aiming at reaching greater productivity, digitalization and operational efficiency standard. In this new era, if compared to automated assembly systems, manual assembly systems (MASs) are still characterized by wide flexibility but poor productivity levels. To reach acceptable performances in terms of both productivity and flexibility, higher automation levels are required to increase the skills and capabilities of the human operators with the aim to design next-generation assembly systems having higher levels of adaptivity and collaboration between people and automation/information technology. In the current literature, such systems are called adaptive automation assembly systems (A3Ss). For A3Ss, few design approaches and industrial prototypes are available. This paper, extending a previous contribution by the Authors, expands the lacking research in the field and proposes a general framework guiding toward A3S effective design and validation. The framework is applied to a full-scale prototype, highlighting its features together with the technical- and human-oriented improvements arising from its adoption. Specifically, evidence from this study show a set of benefits from adopting innovative A3Ss in terms of reduction of the assembly cycle time (about 30%) with a consequent increase of the system productivity (about 45%) as well as relevant improvements of ergonomic posture indicators (about 15%). The definition of a general framework for A3S design and validation and the integration of the productivity and ergonomic analysis of such systems are missing in the current literature, representing an element of innovation. Globally, this research paper provides advanced knowledge to guide research, industrial companies and practitioners in switching from traditional to advanced assembly systems in the emerging Industry 4.0 era matching current industrial and market features.

The pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenance (PdM) has received significant attention from academics and industries. However, practical issues are limiting the implementation of PdM in manufacturing plants. These issues are related to the availability, quantity, and completeness of the collected data, which do not contain all machinery health conditions, are often unprovided with the contextual information needed by ML models, and are huge in terms of gigabytes per minute. As an extension of previous work by the authors, this paper aims to validate the methodology for streaming fault and novelty detection that reduces the quantity of data to transfer and store, allows the automatic collection of contextual information, and recognizes novel system behaviors. Five distinct datasets are collected from the field, and results show that streaming and incremental clustering-based approaches are effective tools for obtaining labeled datasets and real-time feedback on the machinery’s health condition.

Predictive maintenance allows industries to keep their production systems available as much as possible. Reducing unforeseen shutdowns to a level that is close to zero has numerous advantages, including production cost savings, a high quality level of both products and processes, and a high safety level. Studies in this field have focused on a novel approach, prognostic health management (PHM), which relies on condition monitoring (CM) for predicting the remaining useful life (RUL) of a system. However, several issues remain in its application to real industrial contexts, e.g., the difficulties in conducting tests simulating each fault condition, the dynamic nature of industrial environments, and the need to handle large amounts of data collected from machinery. In this paper, a data-driven methodology for PHM implementation is proposed, which has the following characteristics: it is unsupervised, i.e., it does not require any prior knowledge regarding fault behaviors and it does not rely on pre-trained classification models, i.e., it can be applied “from scratch”; it can be applied online due to its low computational effort, which makes it suitable for edge computing; and, it includes all of the steps that are involved in a prognostic program, i.e., feature extraction, health indicator (HI) construction, health stage (HS) division, degradation modelling, and RUL prediction. Finally, the proposed methodology is applied in this study to a rotating component. The study results, in terms of the ability of the proposed approach to make a timely prediction of component fault conditions, are promising.

Industry 4.0 (I4.0) was introduced in 2011, and its advanced enablers strongly affect industrial practices. In the current literature, while several papers offer general reviews on the topic, contributions exploring the evidences coming from the implementation of I4.0 in multi‐sector Small and Medium Enterprises (SMEs) and large enterprises are few and expected. To address this gap, a comprehensive review of the main I4.0 enabling technologies is conducted, focusing on implementation experiences in companies belonging to different sectors. Forty (40) real case studies are analyzed and compared. The results show that 63% of the identified applications involve large enterprises in the transport sector, that is, automotive, aeronautics, and railway, adopting a structured set of enabling technologies. SMEs engaged in I4.0 projects primarily belong to the mechanical engineering sector, and 37% of such projects deals with the preliminary feasibility analysis of introducing a single enabling technology. Conclusions and trends guide researchers and practitioners in understanding the implementation level of I4.0 technologies.