Search

With the rapid development of information technologies, shared manufacturing is proposed to meet the prevailing tendency of servitization and digitalisation in the industry. As the crucial section for performing shared manufacturing, resource monitoring and maintenance aim to detect production exceptions and ensure normal task execution. Existing research mainly uses a resource-centric strategy to acquire production-related data and make decisions for the management of shared resources. The experience data from the users/customers of the shared resources or its similar resources is rarely acquired actively in a cost-effective manner. However, the user/customer's experience data may contain essential knowledge that can be used for effective production performance identification and maintenance. To fill this gap, a hybrid sensing-based approach is proposed to perform the monitoring and maintenance of the shared manufacturing resources. It leverages both the sensor-sensed production data and user/customer-generated data for value creation in a cost-effective manner. Based on the acquired hybrid data, a service model is constructed to achieve the monitoring of the shared manufacturing resource, and a knowledge-based mechanism is designed to perform efficient maintenance. A case study is further presented to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Since innovation in complex product design hinges on thorough engineering knowledge application, high-quality patent recommendations foster innovation in engineering design. However, many patent knowledge recommendation studies perform patent analysis without comprehensive exploration and proper organisation of knowledge, causing a superficial understanding of patents and returning arbitrary results. To mitigate this issue, a deep learning-based approach for patent representation learning and knowledge recommendation is proposed. First, a four-dimensional patent knowledge model is defined to formalise the patent attributes that critically affect the engineering design outcomes, namely patents’ domain(D), function(F), technology(T) and citation(C). Second, to exploit patent knowledge from their content and citation relationships, a representation learning approach integrating Bidirectional Encoder Representations from Transformers(BERT) and Graph Attention Network(GAT) is introduced. Thereafter a patent knowledge space is established in which each patent is characterised by the function, technology, and citation embeddings. Third, a knowledge requirement space is also constructed by vectorising a designer’s search query via BERT model and linking it to a requirement-representing patent based on similarity. Finally, a recommender prototype is developed and showcased by the knowledge recommendation in sealing structure design tasks. Comparative experiments and application cases validate the effectiveness of our method in patent representation learning and knowledge recommendation. [ABSTRACT FROM AUTHOR]

Microglia help limit the progression of Alzheimer's disease (AD) by constraining amyloid-β (Aβ) pathology, effected through a balance of activating and inhibitory intracellular signals delivered by distinct cell surface receptors. Human leukocyte Ig-like receptor B4 (LILRB4) is an inhibitory receptor of the immunoglobulin (Ig) superfamily that is expressed on myeloid cells and recognizes apolipoprotein E (ApoE) among other ligands. Here, we find that LILRB4 is highly expressed in the microglia of patients with AD. Using mice that accumulate Aβ and carry a transgene encompassing a portion of the LILR region that includes LILRB4, we corroborated abundant LILRB4 expression in microglia wrapping around Aβ plaques. Systemic treatment of these mice with an anti-human LILRB4 monoclonal antibody (mAb) reduced Aβ load, mitigated some Aβ-related behavioral abnormalities, enhanced microglia activity, and attenuated expression of interferon-induced genes. In vitro binding experiments established that human LILRB4 binds both human and mouse ApoE and that anti-human LILRB4 mAb blocks such interaction. In silico modeling, biochemical, and mutagenesis analyses identified a loop between the two extracellular Ig domains of LILRB4 required for interaction with mouse ApoE and further indicated that anti-LILRB4 mAb may block LILRB4-mApoE by directly binding this loop. Thus, targeting LILRB4 may be a potential therapeutic avenue for AD. Editor's summary: The microglial function is in part controlled by different lipid-binding receptors. Stimulation of one such activating receptor, triggering receptor expressed on myeloid cells 2 (TREM2), has shown therapeutic effects in preclinical models of Alzheimer's disease (AD). Here, Hou et al. investigated the therapeutic potential of targeting human leukocyte Ig-like receptor B4 (LILRB4). LILRB4 inhibits microglial phagocytosis and was highly expressed in the microglia of patients with AD. Expression of human LILRB4 in a mouse model of AD decreased associations between microglia and amyloid plaques and increased amyloid pathology. These effects could be reversed by LILRB4-specific antibody treatment, suggesting LILRB4 as a potential treatment target for AD. —Daniela Neuhofer [ABSTRACT FROM AUTHOR]

Pavement crack detection in complex scenes presents a significant challenge in achieving precise pixel-level accuracy due to the presence of intricate backgrounds, such as water stains, shadows, and repair grouting, which closely resemble cracks in terms of morphology and colour. Consequently, existing approaches often struggle to differentiate these elements, resulting in misclassification and decreased accuracy in corresponding areas. This paper proposes a novel approach, called the Dual-Stream U-Network (DSU-Net), specifically designed for complex scene crack detection. The DSU-Net model employs a dual-stream framework, enabling improved focus on challenging regions and effectively addressing the issue of low recognition accuracy. To construct a comprehensive dataset, photogrammetry techniques are employed to acquire images of cracks, resulting in a dataset comprising 5000 images. Experimental evaluations demonstrate that the trained DSU-Net model achieves a mean F1 score of 74.17% on a test set, surpassing the performance of the state-of-the-art methods which achieved a score of 68.09%. These findings validate the effectiveness of the proposed algorithm in accurately distinguishing water stains, shadows, repair grouting, and cracks. Additionally, the algorithm successfully performs fine-grained extraction of cracks. The promising results obtained in this study indicate the potential practical applicability of the proposed approach in engineering scenarios. [ABSTRACT FROM AUTHOR]

The paradigm of Smart product-service systems (Smart PSS) has emerged recently owing to the edge-cutting Information and Communication Technology (ICT) and artificial intelligence (AI) techniques. The unique features of Smart PSS including smartness and connectedness, value co-creation and data-driven design manner, enable the collection and analysis of large volume and heterogeneous contextual data to extract useful knowledge. Therefore, requirement elicitation, as a critical process for new solution (i.e. product-service) design, can be conducted in a rather context-aware manner, assured by those massive user-generated data and product-sensed data during the usage stage. Nevertheless, despite a few works on semantic modelling, scarcely any reports on such mechanism in today's smart, connected environment. Aiming to fill this gap, for the first time, a graph-based context-aware requirement elicitation approach considering contextual information within the Smart PSS is proposed. It leverages the pre-defined product, service, and condition ontologies together with Deepwalk technique, to formulate those concepts as nodes and their relationships as the edge of the proposed requirement graph. Implicit stakeholder requirements within a specific context can be further derived based on such interrelationships in a data-driven manner. To demonstrate its feasibility and effectiveness, an example of smart bike share system is addressed to illustrate the requirement elicitation process. It is hoped that this explorative study can offer valuable insights for the service providers who would like to extract requirements not only from the voice of customers but also from the user-generated data and product-sensed data. [ABSTRACT FROM AUTHOR]

In the manufacturing industry, the design of machining processes plays a pivotal role in determining the quality, efficiency, and cost of product manufacturing. Machining process design is progressing towards intelligence to meet the high demands for efficiency and effectiveness in smart manufacturing. Building upon traditional computer-aided process planning, intelligent technologies, such as machine learning and knowledge graphs, have emerged as key drivers in advancing intelligent process design. To address knowledge accumulation, inflexible reuse, and fragmented reasoning in machining process design, this paper organically integrates the structured representation characteristics of the knowledge graph and the perceptual reasoning capabilities of deep reinforcement learning. It introduces an intelligent generation method for machining process design based on knowledge graph and deep reinforcement learning, aiming to achieve unified representation and reasoning reuse for historical process cases and general process rules. The effectiveness of the proposed method is validated through a case study involving the generation of machining process solutions for a specific model of diesel engine components. This research contributes valuable insights to overcoming the limitations of traditional methods and enhancing the efficiency of the machining process design. [ABSTRACT FROM AUTHOR]

Higher sustainability with extended product lifecycle is a tireless pursuit in companies' product design/development endeavours. In this regard, two prevailing concepts, namely the smart circular system and smart product-service system (Smart PSS), have been introduced, respectively. However, most existing studies only focus on the sustainability of physical materials and components, without considering the cyber-physical resources as a whole, let alone an integrated strategy towards the so-called Sustainable Smart PSS. To fill the gap, this paper discusses the key features in Sustainable Smart PSS development from a broadened scope of cyber-physical resources management. A data-driven reversible framework is hereby proposed to sustainably exploit high-value and context-dependent information/knowledge in the development of Sustainable Smart PSS. A four-step context-aware process in the framework, including requirement elicitation, solution recommendation, solution evaluation, and knowledge evolvement, is further introduced to support the decision-making and optimization along the extended or circular lifecycle. An illustrative example is depicted in the sustainable development of a smart 3D printer, which validates the feasibility and advantages of the proposed framework. As an explorative study, it is hoped that this work provides useful insights for Smart PSS development with sustainability concerns in a cyber-physical environment. [ABSTRACT FROM AUTHOR]

Owing to the discontinuous specificity and complexity of architecture design space, the issue of selecting and combining components comprising the engineered system, numerous constraints and associations need to be accounted for, adding up to a complex and substantial cognitive load on the system architects, which makes it challenging to tackle the current demand of adaptive improvements or innovative upgrading of the existing mature architectural solutions. To this end, this paper proposes an intelligent design exploration method for complex system architecture generation with reinforcement learning. The architectural design space (ADS) is identified by defining the dimensions of ADS, including model, quantity, and design chain, as well as the mathematical boundaries and representation to facilitate computable intelligent design exploration. On this basis, by adopting AI techniques primarily based on reinforcement learning, a massive and reliable architectural scheme is rapidly generated, and a more satisfying and robust architectural solution is selected by accessing the fuzzy Pareto frontier. Validation of the method is demonstrated through a case study of a launch vehicle's first and second-stage separation system. This research contributes valuable insights to overcoming the limitations of traditional techniques and enhancing the efficiency of the generative design and decision-making for complex engineered system architecture. [ABSTRACT FROM AUTHOR]

The current demand for aircraft panel assembly fixtures necessitates agile manufacturing solutions. Traditional welding fixtures struggle to meet diverse panel types, high quantities, and short manufacturing cycles. Conversely, reconfigurable flexible assembly fixtures offer universality, efficiency and ease of maintenance but heavily rely on designers' experience, hindering knowledge reuse. Existing research on computer-aided fixture design (CAFD) primarily addresses specialized fixtures, neglecting reconfigurable flexible ones, lacking fixture design knowledge systems. Aiming at the above problems, the study proposes an intelligent design method for the reconfigurable flexible assembly fixture for aircraft panels based on the smart composite jig model (SCJM) and knowledge graph (KG). Firstly, based on the SCJM of the aircraft panel type assembly fixture (PSCJM), a configuration design method is proposed to carry out the multi-level design of reconfigurable assembly fixture to instantiate PSCJM containing fixture configuration rules and a module library based on model definition (MBD). Then, a knowledge retrieval method is proposed to search the suitable fixture design knowledge based on KG, assisting designers in achieving the flexible design of aircraft panel reconfigurable assembly fixtures. Finally, practical engineering design validation confirms the method's feasibility and effectiveness in obtaining the reconfigurable flexible assembly fixture design scheme for aircraft panels. [ABSTRACT FROM AUTHOR]