Innovative Visualization Research Articles

Visualisation Design Ideation with AI: A New Framework, Vocabulary, and Tool

This paper introduces an innovative framework for visualisation design ideation, which includes a collection of terms for creative visualisation design, the five-step process, and an implementation called VisAlchemy. Throughout the visualisation ideation process, individuals engage in exploring various concepts, brainstorming, sketching ideas, prototyping, and experimenting with different methods to visually represent data or information. Sometimes, designers feel incapable of sketching, and the ideation process can be quite lengthy. In such cases, generative AI can provide assistance. However, even with AI, it can be difficult to know which vocabulary to use and how to strategically approach the design process. Our strategy prompts imaginative and structured narratives for generative AI use, facilitating the generation and refinement of visualisation design ideas. We aim to inspire fresh and innovative ideas, encouraging creativity and exploring unconventional concepts. VisAlchemy is a five-step framework: a methodical approach to defining, exploring, and refining prompts to enhance the generative AI process. The framework blends design elements and aesthetics with context and application. In addition, we present a vocabulary set of 300 words, underpinned from a corpus of visualisation design and art papers, along with a demonstration tool called VisAlchemy. The interactive interface of the VisAlchemy tool allows users to adhere to the framework and generate innovative visualisation design concepts. It is built using the SDXL Turbo language model. Finally, we demonstrate its use through case studies and examples and show the transformative power of the framework to create inspired and exciting design ideas through refinement, re-ordering, weighting of words and word rephrasing.

Low-Power Field-Deployable Interdigital Transducer-Based Scanning Laser Doppler Vibrometer for Wall-Thinning Detection in Plates

Lamb waves have become a focal point in ultrasonic testing owing to their potential for long-range and inaccessible detection. However, accurately estimating the flaws in plates using Lamb waves remains challenging because of scattering, mode conversion, and dispersion effects. Recent advances in laser ultrasonic wave techniques have introduced innovative visualization methods that exploit the dispersion effect of Lamb waves to visualize defects via, for example, acoustic wavenumber spectroscopy. In this study, we developed an interdigital transducer (IDT)-based scanning laser Doppler vibrometer (SLDV) system without a power amplifier using a low-power IDT fabricated from lead magnesium niobate–lead zirconate titanate single crystals. To validate the proposed low-power IDT-based SLDV, four different defective plates were measured for defects. A comparison between a conventional IDT-based SLDV, a dry-coupled IDT-based SLDV, and the proposed method demonstrated that the latter is highly reliable for measuring thin plate defects.

Mondrian Abstraction and Language Model Embeddings for Differential Pathway Analysis.

In this study, we introduce the Mondrian Map, an innovative visualization tool inspired by Piet Mondrian's abstract art, to address the complexities inherent in visualizing biological networks. By converting intricate biological data into a structured and intuitive format, the Mondrian Map enables clear and meaningful representations of biological pathways, facilitating a deeper understanding of molecular dynamics. Each pathway is represented by a square whose size corresponds to fold change, with color indicating the direction of regulation (up or down) and statistical significance. The spatial arrangement of pathways is derived from language model embeddings, preserving neighborhood relationships and enabling the identification of clusters of related pathways. Additionally, colored lines highlight potential crosstalk between pathways, with distinctions between short- and long-range functional interactions. In a case study of glioblastoma multiforme (GBM), the Mondrian Map effectively revealed distinct pathway patterns across patient profiles at different stages of disease progression. These insights demonstrate the tool's potential to enhance downstream bioinformatics analysis by providing a more comprehensive and visually accessible overview of pathway interactions, offering new avenues for therapeutic exploration and personalized medicine.

Smart resilience through IoT‐enabled natural disaster management: A COVID‐19 response in São Paulo state

AbstractNatural disaster management approach establishes stages of prevention, preparation, response, and recovery. With the Internet of Things (IoT), Bigdata, Business Intelligence, and other Information Communication Technologies, data can be gathered to support decisions in stages of the response to natural disaster events. In biological natural disasters, the ICTs can also support efforts to promote social distancing, public health, and economic monitoring to face the threads. São Paulo state used IoT in scenarios to face COVID‐19, such as monitoring vehicular interurban mobility, social distancing, and economic activity. Frameworks, strategies, data views, and use cases are presented to support the decision‐making process to face this biological natural disaster. The data‐driven approach supports several purposes, including the communication of social distancing indices, economic recovery, the progression of contagion, and deaths. It also played a pivotal role in fostering transparency initiatives for society and supporting the crisis committee by facilitating situational analyses, and this approach became standard practice for pandemic response. Studies and innovative visualisation perspectives have produced positive outcomes, guiding the decision‐making process through data analysis. Noteworthy use cases were interurban traffic fence monitoring; mapping of virus spreading; tracking the economic impact concerning recovery plans; and, evaluating the effectiveness of public policies.

Multimodal data integration for enhanced longitudinal prediction for cardiac and cerebrovascular events following initial diagnosis of obstructive sleep apnea syndrome.

Obstructive sleep apnea syndrome (OSAS), a prevalent condition, often coexists with intricate metabolic issues and is frequently associated with negative cardiovascular outcomes. We developed a longitudinal prediction model integrating multimodal data for cardiovascular risk stratification of patients with an initial diagnosis of OSAS. We reviewed the data of patients with new-onset OSAS who underwent diagnostic polysomnography between 2018-19. Patients were treated using standard treatment regimens according to clinical practice guidelines. Over a median follow-up of 32 months, 98/729 participants (13.4%) experienced our composite outcome. At a ratio of 7:3, cases were randomly divided into development (n = 510) and validation (n = 219) cohorts. A prediction nomogram was created using six clinical factors - sex, age, diabetes mellitus, history of coronary artery disease, triglyceride-glucose index, and apnea-hypopnea index. The prediction nomogram showed excellent discriminatory power, based on Harrell's C-index values of 0.826 (95% confidence interval (CI) = 0.779-0.873) for the development cohort and 0.877 (95% CI = 0.824-0.93) for the validation cohort. Moreover, comparing the predicted and observed major adverse cardiac and cerebrovascular events in both development and validation cohorts indicated that the prediction nomogram was well-calibrated. Decision curve analysis demonstrated the good clinical applicability of the prediction nomogram. Our findings demonstrated the construction of an innovative visualisation tool that utilises various types of data to predict poor outcomes in Chinese patients diagnosed with OSAS, providing accurate and personalised therapy. Chinese Clinical Trial Registry ChiCTR2300075727.

A Combined Seasonal Mann–Kendall and Innovative Approach for the Trend Analysis of Streamflow Rate in Two Croatian Rivers

Climate change profoundly impacts hydrological systems, particularly in regions such as Croatia, which is renowned for its diverse geography and climatic variability. This study examined the effect of climate change on streamflow rates in two Croatian rivers: Bednja and Gornja Dobra. Using seasonal Mann–Kendall (MK) tests, overall streamflow trends were evaluated. Additionally, innovative polygon trend analysis (IPTA), innovative visualization for innovative trend analysis (IV-ITA), and Bayesian changepoint detection and time series decomposition (BEAST) algorithms were used to assess the trends’ magnitudes and transitions. The seasonal MK analysis identified significant decreasing trends, primarily during summer. The results of IPTA and IV-ITA revealed consistent decreasing trends throughout most months, with a notable increase in September, especially at high flow values. The rivers’ behavior differed between the first and second halves of the month. BEAST analysis detected abrupt changes, including earlier shifts (1951–1968) in the Bednja and more recent ones (2013–2015) in both the Bednja and, to a lesser extent, the Gornja Dobra rivers. This comprehensive approach enhances our understanding of long-term streamflow trends and short-term fluctuations induced by climate change.

Differential Colonization and Mucus Ultrastructure Visualization in Bovine Ileal and Rectal Organoid-Derived Monolayers Exposed to Enterohemorrhagic Escherichia coli.

Enterohemorrhagic Escherichia coli (EHEC) is a critical public health concern due to its role in severe gastrointestinal illnesses in humans, including hemorrhagic colitis and the life-threatening hemolytic uremic syndrome. While highly pathogenic to humans, cattle, the main reservoir for EHEC, often remain asymptomatic carriers, complicating efforts to control its spread. Our study introduces a novel method to investigate EHEC using organoid-derived monolayers from adult bovine ileum and rectum. These polarized epithelial monolayers were exposed to EHEC for four hours, allowing us to perform comparative analyses between the ileal and rectal tissues. Our findings mirrored in vivo observations, showing a higher colonization rate in the rectum compared with the ileum (44.0% vs. 16.5%, p < 0.05). Both tissues exhibited an inflammatory response with increased expression levels of TNF-a (p < 0.05) and a more pronounced increase of IL-8 in the rectum (p < 0.01). Additionally, the impact of EHEC on the mucus barrier varied across these gastrointestinal regions. Innovative visualization techniques helped us study the ultrastructure of mucus, revealing a net-like mucin glycoprotein organization. While further cellular differentiation could enhance model accuracy, our research significantly deepens understanding of EHEC pathogenesis in cattle and informs strategies for the preventative measures and therapeutic interventions.

What are the dominant drivers and optimal thresholds for a healthy ecosystem in the Yellow River Basin, China? from a perspective of nonlinear nexus

Identifying the dominant factors influencing ecosystem health and their optimal thresholds is essential for the management and restoration of ecosystems. Most of the works, however, have less detected the importance level of individual factors, especially their changes over time and scale, and rarely determined their threshold effects on ecosystem health (EH), which seriously hinders the formulation of targeted policies for sustainable ecosystem management. To address these research gaps, we present an innovative visualization approach to reveal importance changes in natural and anthropogenic variables and their nonlinear coupling process with EH in the China’s Yellow River Basin (YRB) in the last two decades. Results show that (i) Although the EH in the YRB has improved slightly in the past 20 years, it is still not optimistic and shows distinct spatial heterogeneity. (ii) The impact of human activities on the ecosystem health of the YRB has increased and increasingly plays a decisive role, while that of the natural aspect has decreased recently. Specifically, environmental factors (slope, NDVI, and annual temperature) are the dominant factors affecting the upstream EH. Midstream EH is significantly affected by the synergistic effect of natural and anthropogenic factors, but the importance of the proportion of built-up land is intensified (ranked from 8th to 4th). Anthropogenic factors exert the greatest influence on downstream EH variation, especially for population density whose importance order rising from 7th to 2nd. (iii) By illustrating the nonlinear response curves of EH at multi-scale, the tipping point caused ecosystem deterioration in the YRB is explored and the optimal thresholds of leading factors oriented towards the most effective ecosystem conservation goal are obtained. These results help precisely identify the current health status of YRB's ecosystem, as well as providing a valuable reference for moderate restoration standards and sustainable ecosystem management.

Thermophoretic particle deposition in a nanofluid flow across a disc with non-fourier heat flux: An investigation using tangent hyperbolic model

Non-Newtonian nanofluids are attracting the attention of researchers and academics due to the high heat transmission rates that they possess. To improve thermal devices and exchangers, the researchers come up with innovative and expense-effective methods. One of the advanced technological approaches that can be utilized to enhance the thermal performance of devices is the utilization of nanofluids. This non- Newtonian nanofluid possesses the advanced properties of increasing heat transfer and destroying harmful bacteria. For this purpose, the present theoretical work is to explore the heat and thermophoretic particle deposition analysis on the tangent hyperbolic nanofluid flow over the rotating porous disk with presence of non-Fourier heat flux model and nanoparticle aggregation effect. Darcy-Forchheimer fluid model is adopted to develop the fluid flow system. Furthermore, the nanofluid’s viscosity and thermal conductivity are expressed through advanced modeling, employing the modified Krieger-Dougherty model for viscosity and the Maxwell-Bruggeman model for thermal conductivity. The nanoparticles and base fluid involved in this context are Molybdenum disulfide ( Mo S 2 ) and Water/carboxyl-methyl cellulose (CMC) respectively. The mathematical representation of the fluid flow and energy propagation involves a system of coupled partial differential equations (PDEs). The system of partial differential equations (PDEs) is transformed into non-dimensional ordinary differential equations (ODEs), which are then solved both analytically and numerically using the Homotopy Analysis Method(HAM) and Runge-Kutta-Fehlberg (RKF) method along with shooting technique. Exploring the graphical representation reveals a comprehensive analysis of key factors influencing velocity, temperature, and concentration. Through innovative visualization, these parameters take center stage, providing insights into their intricate interplay and dynamic relationships. The heat transfer rate is enhanced 0.24% and 1.4% by rising the values of thermal relaxation parameter and Weissenberg number. Also, the mass transfer rate is accelerated 0.8% and 0.14% due to enhancing the values of thermophoretic coefficient and thermophoresis parameter.

An integrated complex T-spherical fuzzy set and soft set model for quantum computing and energy resource planning

This study introduces the Complex T-Spherical Fuzzy Soft Set (CTSFSS), a novel and practical model for representing two-dimensional ambiguous information. This is achieved by integrating the Complex T-Spherical Fuzzy Set (CTSFS) with the Soft Set (SS). The development of the CTSFSS theory is motivated by the absence of neutral membership in complex q-rung orthopair fuzzy soft sets and the limitations of Traditional Spherical Fuzzy Soft Sets (TSFSS) in capturing two-dimensional data. Data storage and processing in the modern technological landscape necessitate sophisticated algorithmic computations and robust representation of information. To this end, computational systems predominantly rely on a binary system structured on two fundamental states: 0 (off) and 1 (on). Moreover, the significance of energy resources and computer-aided tools is underscored in this domain, especially considering the potential impact of quantum computing and advances in energy resources on the evolution of digital technology. In addressing these complexities, we propose Complex T-Spherical Fuzzy Soft Relations (CTSFSRs), formulated through the Cartesian product of two CTSFSSs. These relations are adept at handling complex and uncertain data in real-world scenarios. We define and categorize various types of CTSFSRs, followed by an in-depth analysis of their outcomes. Additionally, this paper introduces innovative visualization techniques based on CTSFSRs, tailored for decision-making processes involving energy resources and quantum computing applications. The efficacy and applicability of these proposed methodologies are substantiated through comparative analysis with existing models.

Research on innovative visualization design of miao costume images in Qiandongnan under aesthetic perspective

Abstract In this paper, we take the images of Miao costumes as the research object, construct the color system of Miao costumes based on the aesthetics perspective, and take the color migration as the research content to realize the visualization and innovative design of Miao costumes. Firstly, typical Miao dress images are obtained by digital acquisition. Then, RGB and HSL color modes are used to extract the colors and mine the color association rules of Miao dresses to construct the color system of Miao dresses. Then, an image segmentation method based on the color system of Miao costumes is proposed to achieve color migration between the color regions of decorative patterns. Finally, the patterns in the dataset of Miao costumes in Qiandongnan are extracted. Based on the classification study, a systematic and in-depth analysis of the color performance of the pattern patterns is conducted to clarify their artistic and aesthetic forms. It is found that the colors of Qiandongnan Miao costume patterns are mostly high-purity and high-brightness colors, of which high-purity colors (7-10) account for the highest proportion, including 16 colors such as earth red, grape purple, pink, and big red, accounting for about 56.5% of the total. The proportion of high brightness colors (7-10) in the colors is the highest, including 13 colors such as beige, goose yellow, grape purple, peach red, etc., accounting for 68.1%. It can be seen from the use of hues in the dress patterns of the Miao people in Qiandongnan that they will match the colors of the patterns according to the “five colors” and highlight a certain color as the dominant color according to the theme. The whole is complete, full of variegated and strong ethnic flavor.

Knowledge Distillation and Transfer Learning Combined for Innovative Visualization Teaching of Non-Heritage Designs

Abstract This study introduces a novel approach by combining knowledge distillation and transfer learning to create a model that, despite its smaller size, approaches the accuracy of its much larger counterparts. It leverages a trained model from a source domain (teacher) to enhance an untrained model in a target domain (student) with significantly fewer parameters. Through transfer learning, we utilize pre-trained deep learning model parameters as initial values. This paper also explores integrating intangible cultural heritage (ICH) information with school curricula, transforming traditional knowledge presentation into intuitive, personalized displays. Our findings highlight that ICH visualization spans nine categories, with traditional arts and crafts leading with 25 items. Interestingly, only 22.58% of students understand Native American culture, pointing towards the potential for educational enhancement. The research suggests designing curriculum with varied teaching activities to improve students’ comprehensive skills.

Experimental investigation on the influence of blast furnace slag basicity and MgO/Al2O3 ratio on flow characteristics using the image measurement method

This study assessed the influence of basicity and the MgO/Al2O3 ratio on the flow characteristics of the CaO-SiO2-Al2O3-MgO blast furnace slag (BFS) system, employing an innovative visualization method. Elevating the basicity from 0.8 to 1.2 increased the critical flow temperature (Tc) from 1286.0 °C to 1335.5 °C and decreased the critical flow velocity (Vc) from 4.18 mm/min to 3.18 mm/min. Adjusting the MgO/Al2O3 ratio led to fluctuations in Tc and Vc around 1313.0 °C and 3.7 mm/min, respectively, demonstrating a negligible impact on BFS flow characteristics. The observed direct correlation between Vc and the temperature range of significant flow characteristic modifications suggests an extended solid-liquid phase transition and a slower discharge of BFS with increasing Vc. Spectroscopic data revealed enhanced flow characteristics by depolymerizing the aluminosilicate structure of BFS with increased basicity. Similarly, an increased MgO/Al2O3 ratio prompted depolymerization but had an insignificant impact on BFS flow characteristics.

Visualization modality for augmented reality guidance of in-depth tumour enucleation procedures.

Recent research studies reported that the employment of wearable augmented reality (AR) systems such as head-mounted displays for the in situ visualisation of ultrasound (US) images can improve the outcomes of US-guided biopsies through reduced procedure completion times and improved accuracy. Here, the authors continue in the direction of recent developments and present the first AR system for guiding an in-depth tumour enucleation procedure under US guidance. The system features an innovative visualisation modality with cutting trajectories that 'sink' into the tissue according to the depth reached by the electric scalpel, tracked in real-time, and a virtual-to-virtual alignment between the scalpel's tip and the trajectory. The system has high accuracy in estimating the scalpel's tip position (mean depth error of 0.4 mm and mean radial error of 1.34 mm). Furthermore, we demonstrated with a preliminary user study that our system allowed us to successfully guide an in-depth tumour enucleation procedure (i.e. preserving the safety margin around the lesion).

Cognitive Soil Digital Twin for Monitoring the Soil Ecosystem: A Conceptual Framework

The digital twin concept has found widespread application across diverse industries. Herein, we present a comprehensive conceptual framework for the cognitive soil digital twin, which embodies the intricate physical reality of the soil ecosystem, aiding in its holistic monitoring and comprehension. The digital twin can seamlessly integrate a multitude of sensor data sources, including field Internet of Things sensors, remote sensing data, field measurements, digital cartography, surveys, and other Earth observation datasets. By virtue of its duality, this digital counterpart facilitates data organisation and rigorous analytical exploration, unravelling the intricacies of physical, chemical, and biological soil constituents while discerning their intricate interrelationships and their impact on ecosystem services. Its potential extends beyond mere data representation, acting as a versatile tool for scenario analysis and enabling the visualisation of diverse environmental impacts, including the effects of climate change and transformations in land use or management practices. Beyond academic circles, the digital twin’s utility extends to a broad spectrum of stakeholders across the entire quadruple helix, encompassing farmers and agronomists, soil researchers, the agro-industry, and policy-makers. By fostering collaboration among these stakeholders, the digital twin catalyses informed decision-making, underpinned by data-driven insights. Moreover, it acts as a testbed for the development of innovative sensors and monitoring frameworks, in addition to providing a platform that can educate users and the broader public using immersive and innovative visualisation tools, such as augmented reality. This innovative framework underscores the imperative of a holistic approach to soil ecosystem monitoring and management, propelling the soil science discipline into an era of unprecedented data integration and predictive modelling, by harnessing the effects of climate change towards the development of efficient decision-making.

Innovative Visualization Approach for Biomechanical Time Series in Stroke Diagnosis Using Explainable Machine Learning Methods: A Proof-of-Concept Study

Stroke remains a predominant cause of mortality and disability worldwide. The endeavor to diagnose stroke through biomechanical time-series data coupled with Artificial Intelligence (AI) poses a formidable challenge, especially amidst constrained participant numbers. The challenge escalates when dealing with small datasets, a common scenario in preliminary medical research. While recent advances have ushered in few-shot learning algorithms adept at handling sparse data, this paper pioneers a distinctive methodology involving a visualization-centric approach to navigating the small-data challenge in diagnosing stroke survivors based on gait-analysis-derived biomechanical data. Employing Siamese neural networks (SNNs), our method transforms a biomechanical time series into visually intuitive images, facilitating a unique analytical lens. The kinematic data encapsulated comprise a spectrum of gait metrics, including movements of the ankle, knee, hip, and center of mass in three dimensions for both paretic and non-paretic legs. Following the visual transformation, the SNN serves as a potent feature extractor, mapping the data into a high-dimensional feature space conducive to classification. The extracted features are subsequently fed into various machine learning (ML) models like support vector machines (SVMs), Random Forest (RF), or neural networks (NN) for classification. In pursuit of heightened interpretability, a cornerstone in medical AI applications, we employ the Grad-CAM (Class Activation Map) tool to visually highlight the critical regions influencing the model’s decision. Our methodology, though exploratory, showcases a promising avenue for leveraging visualized biomechanical data in stroke diagnosis, achieving a perfect classification rate in our preliminary dataset. The visual inspection of generated images elucidates a clear separation of classes (100%), underscoring the potential of this visualization-driven approach in the realm of small data. This proof-of-concept study accentuates the novelty of visual data transformation in enhancing both interpretability and performance in stroke diagnosis using limited data, laying a robust foundation for future research in larger-scale evaluations.

Is Social Tourism a Vector for Destination Resilience to External Shocks? Evidence From Spain

Unpredictable external shocks exacerbate the negative effects usually attributed to cyclical seasonality. Two such recent shocks, the Global Financial Crisis and the COVID-19 pandemic, shifted debates from crisis management toward concerns for greater resilience in visitor economies. Social tourism is an effective stimulus to destination economies and ameliorates some negative effects of seasonality, but there is little evidence on its contributions to greater destination resilience. Furthermore, resilience, a relatively new concept, is poorly defined. We establish a conceptual link between seasonality and resilience through a holistic multivariate analysis of supply, demand and employment patterns. An empirical study examines resilience longitudinally using municipal-level data, applying multivariate analysis and innovative visualization techniques, and assesses how, where and to what degree the Imserso social tourism program has contributed to the greater resilience of Spanish destinations, demonstrating its effectiveness in contributing to resilience in those which are more vulnerable due to high seasonal imbalances.

AlignStatPlot: An R package and online tool for robust sequence alignment statistics and innovative visualization of big data.

Multiple sequence alignment (MSA) is essential for understanding genetic variations controlling phenotypic traits in all living organisms. The post-analysis of MSA results is a difficult step for researchers who do not have programming skills. Especially those working with large scale data and looking for potential variations or variable sample groups. Generating bi-allelic data and the comparison of wild and alternative gene forms are important steps in population genetics. Customising MSA visualisation for a single page view is difficult, making viewing potential indels and variations challenging. There are currently no bioinformatics tools that permit post-MSA analysis, in which data on gene and single nucleotide scales could be combined with gene annotations and used for cluster analysis. We introduce "AlignStatPlot," a new R package and online tool that is well-documented and easy-to use for MSA and post-MSA analysis. This tool performs both traditional and cutting-edge analyses on sequencing data and generates new visualisation methods for MSA results. When compared to currently available tools, AlignStatPlot provides a robust ability to handle and visualise diversity data, while the online version will save time and encourage researchers to focus on explaining their findings. It is a simple tool that can be used in conjunction with population genetics software.

A receptor-centric decision support system for the mitigation of nuclear power atmospheric release incidents

The history of incidents involving nuclear power plants underscores the imperative for robust consequence assessment and countermeasure plans. Additionally, the recent energy crisis has reaffirmed the enduring necessity of nuclear energy. While a host of assessments, planning, and response fundamentals exist, the literature lacks specific directives for their implementation. Notably, despite a wealth of studies employing the entire suite of available tools (i.e., source release, atmospheric dispersion and deposition, food contamination, and human exposure) for hypothetical or actual cases, the majority tend to focus on the source and fate of nucleoids. Given these circumstances, we propose a receptor-centric and data-driven framework to guide the selection and evaluation of such planning. This framework, which utilizes time-dependent source terms and the JRODOS system, is exemplified within a region home to multiple nuclear plants. Significantly, this new approach proved more robust than traditional wind-rose and worst-case methodologies in capturing a broader spectrum of potential outcomes. Though it was possible to prioritize and validate certain countermeasures, such as sheltering and food restrictions, using the innovative visualization methods within the framework, we identified several limitations. These weaknesses, along with potential avenues for future research, are discussed in this study, contributing valuable insights to this crucial field.

Characterising surface roughness of Ti-6Al-4V alloy machined using coated and uncoated carbide tools with variable nose radius by machine learning

A rich literature explores how cutting parameters influence surface roughness in machining different materials using two- or three-dimensional visualisations. Research on Ti-6Al-4V alloy, an important but difficult-to-machine material, is relatively nascent. This research conducts real-life turning operations for Ti-6Al-4V alloy using coated and uncoated carbide inserts with different nose radii and subsequently applies ML techniques to simulate and characterise surface roughness (Ra) for varying cutting parameters — cutting speed (v), feed rate (f), depth of cut (d). Additionally, it presents an innovative visualisation of all three machining parameters’ influences on the surface roughness for Ti-6Al-4V alloy. The results identify Support Vector Machine (SVM) with RBF kernel as a highly potential ML approach to characterise the impact compared to SVM with linear kernel, Random Forest, Deep Learning, and ensemble approaches. The results also demonstrate, for a low feed rate and cutting speed, the surface roughness is better irrespective of the depth of cut and cutting tool materials. For coated carbide with a 0.40 mm nose radius and feed rate of 0.10 mm/rev, for example, Ra values stay within the range of 0.68 to 1.16 mμ for all experimented cutting speeds ranging from 50 m/min to 250 m/min. A similar outcome occurs for other cutting tools. The surface roughness tends to be higher for a higher feed rate. However, the Ra values can decrease even for a high feed rate if the cutting speed exceeds 200 m/min. Overall, the visualisation indicates a nonlinear relationship between machining parameters and surface roughness.