查看更多>>摘要：Nowadays, Internet-of-Things (IoT), big data, and cloud computing technologies allow increasing the throughput and quality of manufacturing systems, bringing to the rise of the Industry 4.0 paradigm. The aim is to leverage the ICT technologies to achieve a flexible customised production with reduced time while avoiding resources waste. In this framework, Zero-Defect Manufacturing (ZDM) concept plays a crucial role in guaranteeing the minimisation of defects and errors in industry processes by trying to act at the first time properly. Due to its importance, this topic has received greater attention during the last two years by the technical literature. Given the increasing number of research works and the several approaches suggested by researcher interested into the topic, this study aims at providing a literature overview of the current trends in the ZDM field from 2018 to 2020. The focus of the work is to provide a state-of-the-art about ZDM strategies, i.e. Detection, Repair, Prediction and Prevention, by analyzing the related most significant works, thus providing a single-strategy analysis and the corresponding most frequently used methods. A brief bibliometric study corroborates the general research patterns and the relevant aspects emerging from each single-strategy analysis. Finally, based on the conducted study, we point out the shortcomings present in the current technical literature to target the future research directions in the ZDM field.
查看更多>>摘要：Fabric defect detection plays a crucial role in fabric inspection and quality control. Convolutional neural networks (CNNs)-based model has been proved successful in various defect inspection applications. However, the sophisticated background texture is still a challenging task for fabric defect detection. To address the texture interference problem, taking advantage of Gabor filter in frequency analysis, we improved the Faster Region-based Convolutional Neural Network (Faster R-CNN) model by embedding Gabor kernels into Faster R-CNN, termed the Genetic Algorithm Gabor Faster R-CNN (Faster GG R-CNN); in addition, a two-stage training method based on Genetic Algorithm (GA) and back-propagation was designed to train the new Faster GG R-CNN model; finally, extensive experimental validations were conducted to evaluate the proposed model. The experimental results show that the proposed Faster GG R-CNN model outperforms the typical Faster R-CNN model in terms of accuracy. The proposed method’ mean average precision (mAP) is 94.57%, compared to 78.98% with the Faster R-CNN.
查看更多>>摘要：Predictive maintenance is an ever-growing topic of interest, spanning different fields and approaches. In the automotive domain, thanks to on-board sensors and the possibility to transmit collected data to the cloud, car manufacturers can deploy predictive maintenance solutions to prevent components malfunctioning and eventually recall to the service the vehicle before the customer experiences the failure. In this paper we present PREPIPE, a data-driven pipeline for predictive maintenance. Given the raw time series of signals recorded by the on-board engine control unit of diesel engines, we exploit PREPIPE to predict the clogging status of the oxygen sensor, a key component of the exhaust system to control combustion efficiency and pollutant emissions. In the design of PREPIPE we deeply investigate: (i) how to choose the best subset of signals to best capture the sensor status, (ii) how much data needs to be collected to make the most accurate prediction, (iii) how to transform the original time series into features suitable for state-of-art classifiers, (iv) how to select the most important features, (v) how to include historical features to predict the clogging status of the sensor. We thoroughly assess PREPIPE performance and compare it with state-of-art deep learning architectures. Our results show that PREPIPE correctly identifies critical situations before the sensor reaches critical conditions. Furthermore, PREPIPE supports domain experts in optimizing the design of data-driven predictive maintenance pipelines with performance comparable to deep learning methodologies while keeping a degree of interpretability.
查看更多>>摘要：This work presents a cognitive analytics platform for anomaly detection which is capable to handle, analyze and exploit resourcefully machine data from a shop-floor of factory, so as to support the emerging and growing needs of manufacturing industry. The introduced system contributes to industrial digitization and creation of smart factories by providing a generic platform which is a complete solution supporting standards-based factory connectivity, data management, various AI models training and comparisons, live predictions and real-time visualizations. The proposed system is built on a micro-service architecture, in order to be extendable and adaptive over time, and contains three core modules, the Data Acquisition, the Knowledge Management and the Predictive maintenance, which contribute to machine failure prediction and activate predictive maintenance procedures, to efficient production schemes and decision making, to monitor anomalies and handle unforeseen conditions, to predict future behaviours on time series etc. The proposed platform utilizes continuous re-training mechanisms enabling a self learning approach for the delivery of AI solutions, usable also for various production data, guaranteeing the quality of results without continuous monitoring and human-resources allocation for AI models’ retraining. This cognitive platform is supported by machine learning techniques and deep learning architectures in order to achieve the desired performance in the management of factory processes and needs. All the information generated by the proposed platform is provided to the end user through a user interface that utilizes advanced visualization techniques.
查看更多>>摘要：In this paper we address the topic of a possible path to standardize the ICT services expected to be delivered by the so-called “Port of the Future”. How the most relevant technologies and Information Systems are used by the Port Communities for their businesses is discussed together with a detailed analysis of the on-going actions carried on by Standard Setting Organizations. Considering the examples given by the C-ITS Platform and the C-Roads programme at EU level, a proposal of contents to be considered in a comprehensive standardization action is given. The innovation services are therefore grouped into four bundles: (i) Vessel & Marine Navigation, (ii) e-Freight & (Intermodal) Logistics, (iii) Passenger Transport, (iv) Environmental sustainability. The standardized version of these applications will be finally labeled as C-Port services. Alongside the standardization plan, a proposal for ranking the ports on the basis of a specially-defined C-Port vector is discussed with the purpose of addressing the well-known lack of consensus around the mathematical definition of the Smart Port Index. Considering the good practice and the background offered by the Port of Livorno in terms of innovation actions, the prospected final user applications are then labeled as Day 1, Day 1.5, and Day 2 services in consideration of the technical and commercial gaps to be filled. As a case study about the evolution in the C-Port vector experienced by the Port of Livorno in the last years will also be discussed.
查看更多>>摘要：A problem in data-driven fault diagnosis of civil aviation hydraulic pumps is that the faulty samples are much fewer than the healthy samples. To solve this problem, this paper develops a data augmentation method, namely empirical mode reconstruction (EMR), to augment faulty samples which preserve the intrinsic components in the original real samples. A significant property of the developed EMR is that the augmented samples are different but share very similar characteristics and category with the corresponding real samples, to properly guide the training of deep learning models, with the ultimate goal of yielding high diagnostic accuracies. First, the faulty training samples are converted to a series of intrinsic mode functions using empirical mode decomposition. Second, an intrinsic mode function is randomly selected and re-scaled with a weight randomly selected from a properly predefined range. Third, these intrinsic mode functions are used to reconstruct the 1-dimensional samples, which serve as the augmented samples. Besides, the mean values and standard deviations of the augmented samples are kept the same with the corresponding original sample. Finally, the efficacy of the developed EMR in imbalanced fault diagnosis of civil aviation hydraulic pumps is validated through a group of experimental comparisons.
查看更多>>摘要：Since the introduction of the concept of “digital twins” (DTs) in 2002, the number of practical applications in different industrial sectors has grown rapidly. Despite the hype surrounding this technology, companies face significant challenges upon deciding to implement DTs in their organizations due to the novelty of the concept. Furthermore, little research on DT has been conducted for the process industry, which may be explained by the high complexity of accurately representing and modeling the physics behind production processes. To consolidate the fragmented literature on the enabling factors and challenges in DT implementation in the process industry, this study organizes the existing studies on DTs with a focus on barriers and enablers. On this basis, this study contributes to the existing body of knowledge on DTs by organizing the DT literature and by proposing conceptual models describing enablers of and barriers to DT implementation, as well as their mutual relationships.
查看更多>>摘要：The remanufacturing sector has already instigated the shift towards the adoption of digital technology, especially enabled by the progressive development of the Industry 4.0 (I4.0) technologies. However, remanufacturing systems are faced with many challenges that are not typically found in traditional manufacturing systems. Inspired by the need to better understand their idiosyncrasies, particular needs and implications, this paper aims to scrutinise current issues and concerns about digital transformation in the remanufacturing systems. In particular, the paper reviews the extant literature to observe: (1) how the I4.0 technologies have so far been used in remanufacturing and (2) the benefits and risks that need to be considered by remanufacturers when adopting the I4.0 technologies. We have elucidated the significance of our findings and subsequently synthesised our thoughts into eight propositions that demystify the mechanisms of how the I4.0 technologies can bring potential benefits when used by remanufacturers to accomplish a portfolio of remanufacturing tasks, and the risks they need to be aware of. This articulation represents contributions to knowledge as it will set out the underpinning of the future human-technology collaboration, which is key in the I4.0 realm.
NSTL
Elsevier