Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
53,694
result(s) for
"Knowledge engineering"
Sort by:
Research on the intelligent design system for automotive panel die based on geometry and knowledge driven
Automotive panel die design is a significant issue in vehicle development, playing a key role in refining quality and efficiency in the entire vehicle evolution process. It also contributes to reducing production costs and meeting the demands of the fashionable and dynamic vehicle market. This article delves into the intricacies of panel die design, focusing on essential issues such as complex three-dimensional (3D) curve and surface processing. A solution for intelligent die design based on geometry and knowledge-driven approaches is proposed. By thoroughly exploring the forming process of panel parts and incorporating die design expertise, a structured design knowledge base is established, which consolidates extensive experience and professional technology in this field. A curve offset algorithm based on progressive iteration is advocated. By adopting a dynamic error sampling algorithm that considers offset distance, the accuracy of the offset curve is ensured. In addition, the method of adjusting the offset direction is adopted to avoid the problem of overlapping offset curves and prevent distortion. Subsequently, a smooth surface is created based on the trimming curve and its offset curve to obtain a parameterized modeling of key non-standard components such as trimming tools. Furthermore, a solution strategy is proposed to handle these dynamic changes and constraints associated with parameter values, ranges, and accuracy requirements of standard components by developing a standard component computer-aided design (CAD) library, which can be seamlessly integrated into various CAD platforms through cloud-based deployment. By integrating die design knowledge, computer-aided geometric design (CAGD) theory, intelligent algorithms, and standard component libraries, a geometric and knowledge-based intelligent design system for automotive panel dies was successfully opened up. After example verification, the efficiency and quality of die design can be upgraded to a large extent.
Journal Article
Triple confidence measurement in knowledge graph with multiple heterogeneous evidences
Knowledge graph (KG) is a representative technique of knowledge engineering, and it is often used in various intelligence applications, which assume that all triples in knowledge graphs (KGs) are correct. However, due to the noise brought by automatic KG construction techniques and the fuzziness of knowledge in specific fields, measuring uncertainty of KGs (i.e., the confidence of each triple being true) is important to the tasks of error detection and fact verification. Existing studies on triple confidence measurement either only relies on explicit evidences or merely depends on embedding evidences, which causes the resulting confidences are not precise enough. To solve this problem, in this paper, we propose a new triple confidence measurement (TCM) method, which combines multiple heterogeneous evidences including explicit evidences (i.e., concept paths and neighbor concept subgraphs) and different embedding evidences acquired by large language model, KG embedding models, contrastive learning, and graph convolutional network. Experiments on different real-world datasets demonstrate not only the superiority of TCM in the tasks of error detection and link prediction, but also the effectiveness of all proposed explicit evidences and embedding evidences.
Journal Article
Sonic skills : listening for knowledge in science, medicine and engineering (1920s-present)
It is common for us today to associate the practice of science primarily with the act of seeing - with staring at computer screens, analyzing graphs, and presenting images. This open access book explains why, indeed, listening for knowledge plays an ambiguous, if fascinating, role in the sciences. For what purposes have scientists, engineers, and physicians listened to the objects of their interest? How did they listen exactly? And why has listening often been contested as a legitimate form of access to scientific knowledge? This concise monograph combines historical and ethnographic evidence about the practices of listening on shop floors, in laboratories, field stations, hospitals, and conference halls, between the 1920s and today.
Book
In-situ prediction of machining errors of thin-walled parts: an engineering knowledge based sparse Bayesian learning approach
Thin-walled parts such as blades are widely used in aerospace field, and their machining quality directly affects the service performance of core components. Due to obvious time-varying nonlinear effect and complex machining system, it is a great challenge to realize accurate and fast prediction of machining errors of such parts. To solve the above problems, an engineering knowledge based sparse Bayesian learning approach is proposed to realize in-situ prediction of machining errors of thin-walled blades. Firstly, an engineering knowledge based strategy is proposed to improve the generalization ability of the model by integrating multi-source engineering knowledge, including machining information, physical information and online monitoring information. Then, principal component analysis method is utilized for the dimensional reduction of features. Sparse Bayesian learning approach is developed for model training, which significantly reduce the complexity of the regression model. Finally, the superiority and effectiveness of the proposed approach have been proven in blade milling experiments. Experimental results show that the average deviation of the proposed in-situ prediction model is about 11 μm, and the model complexity is reduced by 66%.
Journal Article
Handbook of knowledge management for sustainable water systems
\"A comprehensive synthesis of the best practices for management in the vital and rapidly growing field of sustainable water systems Handbook of Knowledge Management for Sustainable Water Systems offers an authoritative resource that goes beyond the current literature to provide an interdisciplinary approach to the topic. The text explores the concept of knowledge management as a key asset and a crucial component of organizational strategy as applied to the sustainability of water systems. Using the knowledge management framework, the authors discuss socio-hydrology sustainable water systems that reflect the present political, economic and technological reality. The book draws on contributors from a number of disciplines including:economic development, financial, systems-networks, IT/IS data/analytics, behavioral, social, water systems, governance systems and related ecosystems. This vital resource: Contains a multifaceted approach that draws on a number of disciplines and contains contributions from experts in their various fields Offers a coherent approach that discusses the dynamic concept of sustainability drawing on data from people, systems and processes of diverse water systems Includes a comprehensive review of the topic and offers a platform for dialog between theory and empirical analysis Explores opportunities for multi-constituent synthesis This book is written for regulators, water utility practitioners, researchers and students interested in the fledgling field of knowledge management and sustainable water systems and those who want to improve the effective and efficient management of a complex water system\"-- Provided by publisher.
Book
A Hybrid Approach to Ontology Modularization
The design of ontologies is a non-trivial task that can simply be reduced to the reuse of one or more existing ontologies. However, since an expert in knowledge engineering would only need a part of the ontology to perform a specific task, obtaining this partition will sometimes require the modularization of existing ontologies. There exist two categories of ontology modularization techniques: partitioning and extraction. This paper describes a new hybrid modularization approach, which combines both categories in an integrated segmentation algorithm, taking advantage of the best of both worlds and capable of building ontology modules that are syntactically and semantically sufficient to achieve a given goal. The segmentation algorithm is based on the hierarchical deep and the semantic threshold, two essential parameters allowing to regulate the taxonomy path of the source ontology, and to control the proportions of the module to be built. Potentially relevant concepts are observed through semantic relationships. The approach has been implemented through a tool named COMET. A validation protocol has been defined to evaluate the quality of the different extracted modules using a number of metrics. The validation is based on a comparative study of the modules generated by COMET, compared to a given reference ontology. Many tests have been conducted one of the findings is that, the density of an ontology which represents the level of its completeness, is an essential property. From the series of tests conducted during our study, we concluded that the denser an ontology is, the denser the module returned by COMET is.
Journal Article