Knowledge-based Process Research Articles

Estimating the health of turbine engine based on the relationship between torque margin and density altitude

We present an anomaly detection method developed for the PHM North America 2024 Conference Data Challenge. This competition is aimed at estimating the health of helicopter turbine engines (PHM Society, 2024). The task includes the estimation of the torque margin (regression) and the health state (binary classification) of turbine engines. We developed an estimation model using a hybrid algorithm that combines data-based machine learning and domain knowledge-based processing. Our method achieved scores over 0.99 for both the testing and validation datasets. based on the calculation rules provided by PHM Society. These results were ranked first among all the participating teams.

Developing an intelligent and sustainable model to improve E-learning satisfaction based on the learner’s personality type: data mining approach in high education systems

PurposeAlthough E-learning has been in use for over two decades, running parallel to traditional learning systems, it has gained increased attention due to its vital role in universities in the wake of the COVID-19 pandemic. The primary challenge within E-learning pertains to the maintenance of sustainable effectiveness and the assurance of stakeholders' satisfaction. This research focuses on an intelligence-driven solution to recommend the most effective approach to education policymakers by considering the unique characteristics of all components within the educational system (course type, student and teacher characteristics, and technological features) to achieve a sustainable E-learning system.Design/methodology/approachThrough a systematic literature review and qualitative content analysis, a conceptual model of the critical components influencing E-learning quality and satisfaction has been developed. The proposed model comprises six main dimensions: usage, service quality, learning system quality, content quality, perceived usefulness, and individual characteristics. These dimensions are further divided into 15 components and 114 sub-components. A data mining process encompassing two scenarios has been designed to prioritize the components impacting E-learning success.FindingsIn the first scenario, data mining techniques identified the most influential components based on the features outlined in the conceptual model. According to the results, the components affecting E-learning quality enhancement in the studied case are “usage purpose, system loyalty, technical and supportive system quality, and student characteristics.” The second scenario examines the impact of individuals' personality types and learning styles on E-learning satisfaction across various aspects (Average System Satisfaction, Overall System Satisfaction, Efficiency and Effectiveness, Skill Enhancement, and Personal Enhancement). The findings reveal that, with an accuracy of over 70%, E-learning satisfaction for diplomat and guard learners is influenced by the alignment between “course learning style” and “student-suggested course learning style.” Conversely, for analyzer and researcher types, satisfaction levels are impacted by the “learning style compatible with their personality type.”Originality/valueImplementing a dynamic model founded on data mining enables educational institutions to personalize the E-learning experience for each individual as much as possible. The study’s findings indicate that “achieving higher satisfaction levels in the E-learning process is not necessarily contingent upon providing a learning style congruent with learners' personality types.” Rather, perceived and suggested learning styles exert a more profound influence. Consequently, providing prescriptive principles for higher education institutions seeking to enhance E-learning quality is inadvisable. Instead, adopting a dynamic, knowledge-based process that furnishes recommendations to policymakers for each course—tailored to the specific course type, teaching records, current processes and technology, and student type—is highly recommended.

A Novel Fuzzy Model for Knowledge-Driven Process Optimization in Renewable Energy Projects

AbstractThis study is aimed at identifying key indicators to increase knowledge-based process optimization for renewable energy projects. Within this context, a novel fuzzy decision-making model is introduced that has two different stages. The first stage is related to the weighting of the knowledge-based determinants of process optimization in investment decisions by using quantum picture fuzzy rough sets (QPFR)-based multi-step wise weight assessment ratio analysis (M-SWARA). On the other side, the second stage consists of ranking the investment alternatives for process optimization in renewable energy projects via the QPFR-based technique for order preference by similarity (TOPSIS) methodology. The main contribution of this study is that a priority analysis is conducted for information-based factors affecting the performance of renewable energy projects. This situation provides an opportunity for the investments to implement appropriate strategies to increase the optimization of these investments. It is concluded that quality is the most essential indicator with respect to the process optimization of these projects. It can be possible to increase the efficiency of these projects by using better quality products. Innovation has an important role in ensuring the use of quality products in environmental sustainability. Owing to new technologies, it is easier to use more effective and innovative products. This condition also contributes to increasing the efficiency of the energy production process. Furthermore, the findings also denote that the most appropriate energy innovation alternative is the variety of clean energy sources. By focusing on different clean energy alternatives, the risk of interruptions in energy generation can be minimized. In other words, the negative impact of climatic conditions on energy production can be lowered significantly with the help of this situation.

Flow modeling and structural characterization in fungal pellets

Fungal pellets are hierarchical systems that can be found in an ample variety of applications. Modeling transport phenomena in this type of systems is a challenging but necessary task to provide knowledge-based processes that improve the outcome of their biotechnological applications. In this work, an upscaled model for total mass and momentum transport in fungal pellets is implemented and analyzed, using elements of the volume averaging and adjoint homogenization methods departing from the governing equations at the microscale in the intracellular and extracellular phases. The biomass is assumed to be composed of a non-Newtonian fluid and the organelles impervious to momentum transport are modeled as a rigid solid phase. The upscaled equations contain effective-medium coefficients, which are predicted from the solution of adjoint closure problems in a three-dimensional periodic domains representative of the microstructure. The construction of these domains was performed for Laccaria trichodermophora based on observations of actual biological structures. The upscaled model was validated with direct numerical simulations in homogeneous portions of the pellets core. It is shown that no significant differences are observed when the dolipores are open or closed to fluid flow. By comparing the predictions of the average velocity in the extracellular phase resulting from the upscaled model with those from the classical Darcy equation (i.e., assuming that the biomass is a solid phase) the contribution of the intracellular fluid phase was evidenced. This work sets the foundations for further studies dedicated to transport phenomena in this type of systems.

Correction: Enabling Configurable Workflows in Smart Environments with Knowledge-based Process Fragment Reuse

Correction: Enabling Configurable Workflows in Smart Environments with Knowledge-based Process Fragment Reuse

Enabling Configurable Workflows in Smart Environments with Knowledge-based Process Fragment Reuse

Enabling Configurable Workflows in Smart Environments with Knowledge-based Process Fragment Reuse

Straightening rollformed profiles by controlled partial rolling

Roll forming is a sheet metal forming process in which flat sheets are incrementally formed into a desired profile geometry. The process is characterized by high material utilization and output. Along with these advantages, process-related longitudinal strains occur, causing profile defects such as bowing and twisting of the profile, which require subsequent straightening. Conventional straightening methods use overbending and twisting to eliminate existing profile defects. However, this approach is purely experience-based and iterative due to the complex interactions between the various bending and twisting operations. Therefore, a closed-loop control of the straightening process is currently not implemented. This can be remedied by the novel knowledge-based straightening method of partial rolling.In this paper, the basic idea of partial rolling will be introduced and the idea of knowledge-based process control will be demonstrated. A simulation model is then presented to test different process control strategies and evaluate their impact on the profile defects. Finally, an outlook is given on how a closed-loop controlled partial rolling process could be set up in a real process.

Towards a mechanistic understanding of the floating catalyst CVD of CNTs: Interplay between catalyst particle nucleation, growth and deactivation

The chemical vapor deposition (CVD) of carbon nanotubes (CNTs) with the floating catalyst technique, using ferrocene as catalyst, is computationally investigated from its mechanistic perspective. The present work presents a novel model dealing with the phenomena taking place in the bulk of a floating catalyst CVD reactor. The developed model incorporates the gas flow, heat transfer and species transport phenomena, coupled with reaction mechanisms and kinetics, as well as the catalyst particle formation and growth dynamics. The novelty of the approach lies on the inclusion of carbon species deposition on the catalyst particle surface, which have a crucial effect on the particle growth and catalyst deactivation, leading to the termination of CNT growth on the particles. The model predictions are directly compared with experimental results from the literature for the same process and for a range of process parameters, showing a very good agreement. The computational model not only successfully predicts the experimental behavior but also reveals the effect of individual mechanisms on the inhibition of particle growth, catalyst deactivation and CNT growth. In this way, the model provides an in-depth mechanistic understanding of the mechanisms in the reactor bulk, which is currently missing, thus paving the way towards the knowledge-based process design and optimization and the possibility of using more sustainable or environmentally-friendly precursors and catalysts which have not been studied experimentally in detail.

Knowledge-Aware Learning Framework Based on Schema Theory to Complement Large Learning Models

ABSTRACT Despite tremendous recent progress, extant artificial intelligence (AI) still falls short of matching human learning in effectiveness and efficiency. One fundamental disparity is that humans possess a wealth of prior knowledge, while AI lacks the essential commonsense knowledge required for learning tasks. Guided by schema theory, we employ the design science research methodology to introduce a novel knowledge-aware learning framework to harness the knowledge-based processes in human learning. Unlike existing pre-trained large language models (LLMs) and knowledge-aware approaches that treat knowledge in considerably different ways from humans, our theoretically grounded framework closely mimics how humans acquire, represent, activate, and utilize knowledge. The extensive evaluations in the context of text analytics tasks demonstrate that our design achieves comparable performance to the state-of-the-art LLMs and enhances model generalizability and learning efficiency. This study takes a step forward by bringing cognitive science into building cognitively plausible AI and human-AI collaboration research.

Lithium-ion battery cell formation: status and future directions towards a knowledge-based process design

This review examines the key process of lithium-ion battery cell formation. Influencing factors, challenges, experimental and simulation tools required for knowledge-based process design of current and emerging battery technologies are addressed.

Guiding pre-service teachers’ visual attention through instructional settings: an eye-tracking study

In complex classroom situations, pre-service teachers often struggle to identify relevant information. Consequently, classroom videos are widely used to support pre-service teachers’ professional vision. However, pre-service teachers need instructional guidance to attend to relevant information in classroom videos. Previous studies identified a specific task instruction and prompts as promising instructions to enhance pre-service teachers’ professional vision. This mixed-methods eye-tracking study aimed to compare pre-service teachers’ visual attention to information relevant for classroom management in one of three instructional conditions. Participants viewed two classroom videos and clicked a button whenever they identified situations relevant to classroom management in the videos. They got either (1) a specific task instruction before video viewing (n = 45), (2) attention-guiding prompts during video viewing (n = 45), or (3) a general task instruction (n = 45) before video viewing as a control group. We expected a specific task instruction and prompts to better guide participants’ visual attention compared to a general task instruction before video viewing because both experimental conditions contained informational cues to focus on specific dimensions of classroom management. As both a specific task and prompts were assumed to activate cognitive schemata, resulting in knowledge-based processing of visual information, we expected the specific task instruction to have a similar attention-guiding effect as prompts during video viewing. Measurements were conducted on an outcome level (mouse clicks) and on a process level (eye tracking). Findings confirmed our hypotheses on an outcome level and in part on a process level regarding participants’ gaze relational index. Nevertheless, in a disruptive classroom situation, participants of the prompting condition showed better attentional performance than participants of the other conditions regarding a higher number of fixation and a shorter time to first fixation on disruptive students. Further qualitative analyses revealed that, when observing classroom videos without instructional guidance, pre-service teachers were less likely to identify disruptive situations in the video and more likely to attend to other situations of classroom management concerning the teachers’ action. We discuss advantages of both attention-guiding instructions for pre-service teacher education in terms of the economy of implementation and the salience of situations.

Open problems in PDE models for knowledge-based animal movement via nonlocal perception and cognitive mapping

The inclusion of cognitive processes, such as perception, learning and memory, are inevitable in mechanistic animal movement modelling. Cognition is the unique feature that distinguishes animal movement from mere particle movement in chemistry or physics. Hence, it is essential to incorporate such knowledge-based processes into animal movement models. Here, we summarize popular deterministic mathematical models derived from first principles that begin to incorporate such influences on movement behaviour mechanisms. Most generally, these models take the form of nonlocal reaction-diffusion-advection equations, where the nonlocality may appear in the spatial domain, the temporal domain, or both. Mathematical rules of thumb are provided to judge the model rationality, to aid in model development or interpretation, and to streamline an understanding of the range of difficulty in possible model conceptions. To emphasize the importance of biological conclusions drawn from these models, we briefly present available mathematical techniques and introduce some existing "measures of success" to compare and contrast the possible predictions and outcomes. Throughout the review, we propose a large number of open problems relevant to this relatively new area, ranging from precise technical mathematical challenges, to more broad conceptual challenges at the cross-section between mathematics and ecology. This review paper is expected to act as a synthesis of existing efforts while also pushing the boundaries of current modelling perspectives to better understand the influence of cognitive movement mechanisms on movement behaviours and space use outcomes.

Context-driven ontology-based risk identification for onshore wind farm projects: A domain-specific approach

Risk identification is a knowledge-based process that requires the time-consuming and laborious identification of project-specific risk factors. Current practices for risk identification in construction rely heavily on an expert’s subjective knowledge of the current project and of similar historical projects to determine if a risk may affect the project under study. When quantitative risk-related data are available, they are often stored across multiple sources and in different types of documents complicating data sharing and reuse. The present study introduces an ontology-based approach for construction risk identification that maps and automates the representation of project context and risk information, thereby enhancing the storage, sharing, and reuse of knowledge for the purpose of risk identification. The study also presents a novel wind farm construction project risk ontology that has been validated by a group of industry experts. The resulting ontology-based risk identification approach is able to accommodate project context in the risk identification process and, through implementation of the proposed approach, has identified risk factors that affect the construction of onshore wind farm projects.

Planning for Health Equity: How Municipal Strategic Documents and Project Plans Reflect Intentions Instructed by the Norwegian Public Health Act

The Norwegian Public Health Act (PHA) mandates municipalities to integrate a systematic, knowledge-based, cross-sectoral approach aimed at levelling the social gradient in health. This study aimed to describe and analyse how the intentions of the PHA are addressed in municipal plans and project-planning documents. A document analysis of municipal plans and project documents extracted from four municipalities in Central Norway was employed and complemented with deductive, qualitative content analysis. Findings indicate awareness of public health work as a whole-of-municipality responsibility. Systematic knowledge-based processes that make use of relevant data in planning and decision-making processes are described across municipality projects and plans. Multisectoral working groups are set up at a project level; however, opportunities for further improvements arise in respect to the anchor of these structures and systematic knowledge-based working procedures in the wider municipal context. Public health process aims (systematic knowledge-based approach, cross-sectoral governance) receive more attention than outcome aims (health equity) in both program documents and municipal plans. Only very rarely does the document hold operationalizations of how to achieve health equity. As such, effort placed on cross-administrative levels and sectors to promote structures for health equity is still needed.

Research on the Construction of Safety Information Ontology Knowledge Base and Accident Reasoning for Complex Hazardous Production Systems-Taking Methanol Production Process as an Example

Taking methanol production as an example, the concept of “ontology” is introduced to construct a safety knowledge ontology, and a safety information knowledge base is created with the help of the Protégé software. These can be used to efficiently handle the massive safety information data of dangerous chemical enterprises, associate all kinds of miscellaneous information, and improve the level of safety management. An accident tree reasoning model is designed to determine the cause of the accident using accident tree reasoning, and to mine the vast knowledge of safety information, according to safety information knowledge and accident tree analysis theory. Using these methods, the storage, processing, and reuse of safety information are realized, the efficiency of safety management can be improved, and the defects caused by incomplete personnel knowledge structure can be avoided.

Knowledge-Based Process Design Optimization in Blisk Manufacturing

Abstract The manufacturing process of blade-integrated disks (blisks) represents one of the most challenging tasks in turbomachinery manufacturing. The requirement is to machine complex, thin-walled blade geometries with high aspect ratios made of difficult-to-cut materials. In addition, extremely tight tolerances are required, since the smallest deviations can lead to a reduction in efficiency of the blisk in the later use. Nowadays, the ramp-up phase for the manufacturing of a new blisk is time and cost-intensive. To find a suitable manufacturing process that meets the required tolerances of the blisk, many experimental tests with different process parameters and strategies are necessary. The used approach is often trial and error, which offers limited testing opportunities, is time-consuming and waste of resources. Therefore, the objective of this paper is to develop a knowledge-based process design optimization in blisk manufacturing. For this purpose, this paper picks up the results from our previous work. Based on these results, an experimental validation of the two process design tasks “number of blocks” and “block transition” is conducted. As part of the validation, the results of machining tests on a demonstrator blisk made of Inconel 718 are presented and discussed.

IT and Strategic Human Capital: Impact on Knowledge-Based Processes, Networks, and Outcomes

Advancements in information technology (IT) can have profound impacts on the development and management of human capital. Extant research has examined how human capital in markets and organizations are shaped by increased digitization and the deployment of strategies relying on collection and analysis of big data, cloud computing, social media, Internet of Things (IoT), and the like. In knowledge-intensive settings, however, IT-enabled mechanisms have heterogenous impacts on issues related to human capital. Although IT potentially expands capacity for collection, storage, and utilization of knowledge, some firms and individuals successfully leverage technology and information systems while others do not--or are even possibly left worse off. This symposium contributes to examining why such discrepancies may exist by shedding light on the market and organizational processes that underlie the intersection of IT and knowledge-based processes, networks, and outcomes as they relate to issues in strategic human capital. Can Social Media Alleviate Inequality? Evidence from Venture Capital Financing Presenter: Gavin Wang; Wharton OPIM Presenter: Lynn Wu; The Wharton School, U. of Pennsylvania Presenter: Lorin Hitt; U. of Pennsylvania Are Knowledge Sharing and Learning Tradeoffs? Linking Performance Incentives with KMS Usage Presenter: Sae-Seul Park; Carnegie Mellon U. - Tepper School of Business Cloud Adoption and Strategic Human Capital: Evidence from Norway Presenter: Derrick Choe; - Presenter: Amir Sasson; BI Norwegian Business School Presenter: Robert Channing Seamans; NYU Stern Hunting For Talent: Firm-Driven Labor Market Search in the United States Presenter: Ines Black; - Presenter: Sharique Hasan; Fuqua School of Business, Duke U.

Modeling Medical Guidelines by Prova and SHACL Accessing FHIR/RDF. Use Case: The Medical ABCDE Approach.

Decision-making based on so-called medical guidelines supported by semantic AI solutions is an essential and significant task for medical personnel in both a pre-clinical setting and an inner-clinical environment. Semantic representations of medical guidelines and Fast Healthcare Interoperability Resources (FHIR) using Semantic Web technologies, i.e., Resource Description Framework (RDF), rules (RuleML and Prova), and Shape Constraint Language (SHACL), provide a semantic knowledge base for the decision-making process and ease technical implementation and automation tasks. Current medical decision support systems lack Semantic Web integration using FHIR-RDF representations as a data source. In this paper, we implement a particular medical guideline using two different approaches: Prova [8] and SHACL [13]. We generate a series of raw FHIR-data for a selected guideline, the ABCDE approach, and compare the implemented two programs' (Prova and SHACL) results. Both approaches deliver the same results in terms of content. Both may be used within a distributed medical environment depending on the need of organizations.

Inner carbon black porosity as characteristic parameter for the microstructure of lithium-ion electrodes and its effect on physical and electrochemical properties

The conductive network within a lithium-ion battery electrode is mainly influenced by the process parameters chosen for the dry mixing and wet dispersing step during the production of a coatable electrode slurry, consisting of well-defined components. This conductive network, which results from the electrode's microstructure, plays a major role for the resulting battery cell performance, especially for high performance and power applications. Notable differences can be observed in the subsequently manufactured electrodes due to process-related modifications in the carbon black agglomerate size; mechanical, electrical, and, thus, electrochemical properties are significantly changing with the process parameters set. To allow for a direct correlation of these properties with the electrode structure, a characteristic parameter to describe the carbon black structure in electrode coatings is developed. Based on mercury intrusion measurements, the internal porosity of carbon black particles was determined as a characteristic parameter for the conductive microstructure. For a wide variety of lithium-ion battery cathode samples, the carbon black porosity can be well related to important electrode properties. This underscores the relevance of this carbon black-based microstructure parameter for a knowledge-based process and product optimization.

What to buy, Pepper? – Bridging the Physical and the Digital World with Recommendations from Humanoid Robots

ABSTRACT While e-commerce has flourished in the past decades, brick-and-mortar retail stores face increasing challenges in attracting customers. Prior research indicates that humanoid robots may constitute a promising means to counteract this development. However, their capability to acquire and make use of rich information from the physical world (e.g. regarding customers’ physical characteristics) in combination with knowledge from (online) databases has not been adequately exploited yet. Thus, we aim at bringing together the best of the physical and the digital world by supplementing the traditional consultation process in brick-and-mortar retail stores with humanoid robots. Following a design-oriented approach, we propose a novel knowledge-based humanoid robot recommender process. We demonstrate our approach in cooperation with an optician and evaluate it using a customer survey and expert interviews. Results show that the approach achieves the design objectives and yields high customer satisfaction.