Hasil untuk "Hydraulic engineering"

Francisco Leiva, Claudio Canales, Michelle Valenzuela et al.

This paper presents a data-driven methodology for the control of static hydraulic impact hammers, also known as rock breakers, which are commonly used in the mining industry. The task addressed in this work is that of controlling the rock-breaker so its end-effector reaches arbitrary target poses, which is required in normal operation to place the hammer on top of rocks that need to be fractured. The proposed approach considers several constraints, such as unobserved state variables due to limited sensing and the strict requirement of using a discrete control interface at the joint level. First, the proposed methodology addresses the problem of system identification to obtain an approximate dynamic model of the hydraulic arm. This is done via supervised learning, using only teleoperation data. The learned dynamic model is then exploited to obtain a controller capable of reaching target end-effector poses. For policy synthesis, both reinforcement learning (RL) and model predictive control (MPC) algorithms are utilized and contrasted. As a case study, we consider the automation of a Bobcat E10 mini-excavator arm with a hydraulic impact hammer attached as end-effector. Using this machine, both the system identification and policy synthesis stages are studied in simulation and in the real world. The best RL-based policy consistently reaches target end-effector poses with position errors below 12 cm and pitch angle errors below 0.08 rad in the real world. Considering that the impact hammer has a 4 cm diameter chisel, this level of precision is sufficient for breaking rocks. Notably, this is accomplished by relying only on approximately 68 min of teleoperation data to train and 8 min to evaluate the dynamic model, and without performing any adjustments for a successful policy Sim2Real transfer. A demonstration of policy execution in the real world can be found in https://youtu.be/e-7tDhZ4ZgA.

Al Muttakin, Saikat Mondal, Chanchal K. Roy

Replication packages are crucial for enabling transparency, validation, and reuse in software engineering (SE) research. While artifact sharing is now a standard practice and even expected at premier SE venues such as ICSE, the practical usability of these replication packages remain underexplored. In particular, there is a marked lack of studies that comprehensively examine the executability and reproducibility of replication packages in SE research. In this paper, we aim to fill this gap by evaluating 100 replication packages published in ICSE proceedings over the past decade (2015 - 2024). We assess the (1) executability of the replication packages, (2) efforts and modifications required to execute them, (3) challenges that prevent executability, and (4) reproducibility of the original findings for those that are executable. We spent approximately 650 person-hours in total to execute the artifacts and reproduce the study findings. Our analysis shows that only 40 of the 100 evaluated artifacts were fully executable. Among these, 32.5% ran without any modification. However, even executable artifacts required varying levels of effort: 17.5% required low effort, while 82.5% required moderate to high effort to execute successfully. We identified five common types of modifications and 13 challenges that lead to execution failure, encompassing environmental, documentation, and structural issues. Among the executable artifacts, only 35% (14 out of 40) reproduced the original results. These findings highlight a notable gap between artifact availability, executability, and reproducibility. Our study proposes three actionable guidelines to improve the preparation, documentation, and review of research artifacts, thereby strengthening the rigor and sustainability of open science practices in SE research.

WEI Huanwei, ZHAO Jizhang, ZHENG Xiao et al.

ObjectiveWind energy plays a crucial role in achieving sustainable energy goals. As a critical structural component, the wind turbine foundation significantly influences the operational stability, safety, and long-term performance of wind turbine systems. However, structural health monitoring (SHM) of wind turbine foundations often faces challenges with data integrity due to environmental factors, sensor malfunctions, or data transmission issues. These missing data can severely impact the accuracy of structural health assessments, thereby affecting maintenance decisions and operational safety. To tackle the persistent data gaps in the monitoring system of adjustable wind turbine foundations, this study introduces a frequency-space-time domain attention network (FST-ATTNet). This model is designed to enhance the modeling capabilities for complex time-series data, improve the accuracy of missing data reconstruction, and ensure the reliability of health monitoring, ultimately guaranteeing wind turbines' safe and efficient operation. Moreover, it presents potential solutions for similar data reconstruction challenges across various engineering disciplines.MethodsThe FST-ATTNet model introduces an innovative data repair framework by integrating features from the frequency, time, and spatial domains. In the frequency domain, the model employs discrete cosine transform (DCT) to extract periodic and global patterns from time series data, effectively mitigating the high-frequency noise caused by the Gibbs phenomenon in traditional discrete Fourier transform (DFT). A frequency-domain attention mechanism is introduced to enhance this process, adaptively assigning weights to frequency components and prioritizing those most relevant for data reconstruction. In the time domain, Bidirectional Gated Recurrent Units (BiGRU) capture both forward and backward dependencies within the time series, ensuring a comprehensive understanding of local sequence patterns. The Kolmogorov-Arnold Network (KAN) incorporates a B-spline activation function, further enhancing the model's ability to capture complex nonlinear temporal changes. In the spatial domain, the Temporal Convolutional Network (TCN) models long-range dependencies by expanding causal convolutions, thereby capturing local and global spatial relationships. The Squeeze-and-Excitation Network (SENet) further boosts spatial feature extraction by dynamically adjusting the importance of different feature channels. By combining these various attention mechanisms, FST-ATTNet successfully integrates frequency, time, and spatial domain features, achieving superior modeling of complex time series patterns and robust reconstruction of missing data. The model is validated using monitoring data of the measured strain on a pile-based adjustable wind turbine foundation, and its performance is evaluated using the coefficient of determination (<italic>R</italic>²) and mean squared error (<italic>MSE</italic>) metrics.Results and Discussions　Validation experiments based on measured data show that FST-ATTNet has the following advantages: (1) Superior performance compared to traditional models: FST-ATTNet outperforms traditional sequence models in data reconstruction tasks, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional GRU (BiGRU), Temporal Convolutional Network (TCN), and Transformer, achieving excellent results with <italic>R</italic>² of 0.98 and <italic>MSE</italic> of 0.66. In contrast, the <italic>R</italic>² of LSTM and GRU models is only 0.86, and the <italic>MSE</italic> is 2.35 and 2.34, respectively, which are limited by their unidirectional or local feature extraction capabilities. The Transformer model performs the worst, with <italic>R</italic>² of 0.72 and <italic>MSE</italic> as high as 2.77, likely due to its inability to effectively capture local patterns and frequency domain features in multivariate time series data. FST-ATTNet, through deep integration of frequency, time, and spatial information, can capture complex patterns, including periodicity, local dynamics, and long-term dependencies, significantly improving reconstruction accuracy. (2) Robustness in high missing-rate scenarios: The model excels in handling severe data-missing scenarios. In the continuous data missing test, even with a missing rate as high as 40%, FST-ATTNet maintains high reconstruction accuracy with <italic>R</italic>² of 0.94 and <italic>MSE</italic> of 0.95. At the 45% missing rate, performance slightly declines, with <italic>R</italic>² of 0.87 and <italic>MSE</italic> of 1.31, but still outperforms other models. In the feature missing test, when 25% of the monitoring features are entirely missing, the model achieves <italic>R</italic>² of 0.91 and <italic>MSE</italic> of 0.75, demonstrating its ability to handle complex multi-feature missing scenarios commonly found in actual monitoring systems. (3) Insights from ablation experiments: Ablation experiments provide key insights into the contribution of each component of FST-ATTNet. After removing the frequency-domain enhanced attention mechanism, <italic>R</italic>² decreases to 0.92, and <italic>MSE</italic> increases to 1.13. After removing SENet, <italic>R</italic>² is 0.91, and <italic>MSE</italic> is 1.22, indicating that these attention mechanisms play a crucial role in feature enhancement. Removing all attention mechanisms results in further performance degradation, with <italic>R</italic>² of 0.90 and <italic>MSE</italic> of 1.20, highlighting their importance in the prioritization of selective features. Removing the KAN network results in <italic>R</italic>² of 0.92 and <italic>MSE</italic> of 1.09, indicating its contribution to modeling complex time series patterns. Using only frequency domain, time domain, or spatial information results in significant performance drops, with <italic>R</italic>² of 0.75, 0.68, and 0.86, respectively, and <italic>MSE</italic> of 1.98, 2.44, and 1.33, indicating the necessity of integrating frequency, time, or spatial information. Spatial information is especially critical in high-missing scenarios. (4) Applicability of the model: To evaluate the model's applicability, FST-ATTNet was applied to anchor cable monitoring data with a missing rate of up to 50%, achieving excellent results with <italic>R</italic>² of 0.92 and <italic>MSE</italic> of 0.80. The model achieved near-perfect reconstruction for datasets with strong periodicity at a 25% missing rate (<italic>R</italic>² = 0.97, <italic>MSE</italic> = 0.40). However, performance slightly declined at a 50% missing rate (<italic>R</italic>² = 0.92, <italic>MSE</italic> = 0.80), with deviations at the peaks primarily due to the training data not fully covering the entire cycle. Nonetheless, FST-ATTNet demonstrates adaptability across different monitoring scenarios and a unique ability to handle cyclic patterns in periodic data reconstruction.ConclusionsThe FST-ATTNet model offers a reliable and robust solution to the problem of continuous data loss in the health monitoring of pile-type adjustable wind turbine foundations. By deeply integrating frequency, time, and spatial domain information and incorporating advanced attention mechanisms, the model achieves exceptional reconstruction accuracy in high missing-rate scenarios, significantly outperforming traditional sequence models. Furthermore, the successful application of the model to other monitoring datasets (such as anchor cable data) demonstrates its versatility and broad applicability in structural health monitoring. FST-ATTNet not only enhances the reliability of wind turbine foundation monitoring but also provides innovative solutions to similar data repair challenges in other engineering domains, offering crucial support for the safety and efficiency of wind turbine systems.

Runjuan Zhou, Penghui Li, Ming Zhang

The sustainable recovery of phosphate from aqueous systems while simultaneously valorizing industrial and biological wastes remains a critical environmental challenge. Herein, we developed an innovative red mud-modified water hyacinth biochar (RM-BC) for phosphate recovery and subsequent resource utilization. Systematic investigations revealed that the optimized RM-BC exhibited exceptional phosphate adsorption performance, achieving 99.83 % removal efficiency. RM-BC demonstrated rapid uptake kinetics (89.39 % recovery within 120 min) and maintained robust performance (>70 % efficiency) across a wide pH range (3−11). Kinetic and isotherm analyses indicated that the adsorption process followed pseudo-second-order kinetics and the Freundlich model, suggesting multilayer adsorption on heterogeneous surfaces. Thermodynamic studies confirmed the spontaneous and endothermic nature of the process, with enhanced efficiency at higher temperatures. Advanced characterization elucidated the mechanisms, including pore filling, surface precipitation, complexation, and electrostatic interactions. The phosphorus-laden biochar (RM-BC-P) showed excellent environmental compatibility, with heavy metal leaching levels below regulatory limits, qualifying it as a safe soil amendment. Furthermore, RM-BC-P exhibited controlled phosphorus release characteristics, demonstrating dual functionality as both a slow-release fertilizer and heavy metal immobilization agent in contaminated soils. This work provides fundamental insights into waste-derived adsorbent design and presents a sustainable strategy for simultaneous phosphate recovery and waste valorization.

Fuchen Teng, Yong Cheng Sie, Chihping Kuo

Compared with natural soils, frozen soil, which is the primary product of artificial ground freezing (AGF) engineering, is typically impermeable and exhibits superior shear strength. This study investigated the formation and frost heave behavior of frozen soil material under rapid freezing conditions using liquid nitrogen (LN2). Unlike most studies, which have focused on the slower brine freezing method, this research highlights the unique effects of the faster LN2 freezing method. A six-day field experiment was conducted, which integrated nondestructive monitoring techniques such as electrical resistivity tomography (ERT). This method enables detailed spatial and temporal visualization of subsurface resistivity changes. Numerical simulations were performed using the frozen and unfrozen soil model (FUS) to analyze the thermalhydraulicmechanical interactions within the soil during freezing. The results revealed that the temperature of the soil within a distance of 0.5 m from the freezing pipes fell below zero in only six days, resulting in a maximum displacement of 60 mm in the ground. Discontinuous frost heave displacements also occurred. Numerical simulations revealed discrepancies between the simulated and measured data because the soil at depths of 4–7 m was not completely frozen due to the presence of soil and groundwater conditions that were resistant to freezing. This study bridges the knowledge gap in LN2 artificial ground freezing and provides practical guidance for its application under challenging geotechnical conditions.

Hongqi Wang, Zixia Liu, Jingyun Feng et al.

ABSTRACT Amidst intensifying climate change, flash floods are becoming more recurrent, posing significant threats to safety and assets, especially in mountainous areas. Given the non‐negligible influence of bridges on flash floods, this research capitalized on fluid dynamics simulations to examine the mechanisms by which six bridges within the investigation zone affect the evolution of flash floods. Moreover, bridge blockage from debris accumulation was methodically investigated under multiple return periods. Results indicated that during the two historical floods, the bridges altered the distribution pattern of flash floods from various flood elements, including the backwater effect, flow velocity, and inundation. It is noteworthy that the spillway bridge (M1) notably raised water levels and slowed flows, whereas the influence of other bridges on flood dynamics was more muted. The presence of six bridges resulted in expanded flooded areas, particularly near the upstream bridges, raising risks for Qishi Village. Furthermore, the increasing blockage ratios at bridge B2 during multiple return periods exacerbated the impacts on flood elements, consequently amplifying the disaster of flash floods. This research strongly emphasizes the importance of incorporating bridges and their blockages into flood risk management. It further provides technical insights to bolster the basin's resilience against extreme hydrological events.

Alvaro Paz, Mahdi Hejrati, Pauli Mustalahti et al.

Heavy-duty hydraulic manipulators (HHMs) operate under strict physical and safety-critical constraints due to their large size, high power, and complex nonlinear dynamics. Ensuring that both joint-level and end-effector trajectories remain compliant with actuator capabilities, such as force, velocity, and position limits, is essential for safe and reliable operation, yet remains largely underexplored in real-time control frameworks. This paper presents a nonlinear model predictive control (NMPC) framework designed to guarantee constraint satisfaction throughout the full nonlinear dynamics of HHMs, while running at a real-time control frequency of 1 kHz. The proposed method combines a multiple-shooting strategy with real-time sensor feedback, and is supported by a robust low-level controller based on virtual decomposition control (VDC) for precise joint tracking. Experimental validation on a full-scale hydraulic manipulator shows that the NMPC framework not only enforces actuator constraints at the joint level, but also ensures constraint-compliant motion in Cartesian space for the end-effector. These results demonstrate the method's capability to deliver high-accuracy trajectory tracking while strictly respecting safety-critical limits, setting a new benchmark for real-time control in large-scale hydraulic systems.

Jiajie Guo, Muhammad Bilal, Yuying Qiu et al.

As autonomous vehicles and the other supporting infrastructures (e.g., smart cities and intelligent transportation systems) become more commonplace, the Internet of Vehicles (IoV) is getting increasingly prevalent. There have been attempts to utilize Digital Twins (DTs) to facilitate the design, evaluation, and deployment of IoV-based systems, for example by supporting high-fidelity modeling, real-time monitoring, and advanced predictive capabilities. However, the literature review undertaken in this paper suggests that integrating DTs into IoV-based system design and deployment remains an understudied topic. In addition, this paper explains how DTs can benefit IoV system designers and implementers, as well as describes several challenges and opportunities for future researchers.

Renato Amorim, Gabriele Villarini

Abstract The detection of nonstationarities in partial duration time series (PDS) depends on several factors, including the length of the time series, the selected statistical test, and the heaviness of the tail of the distribution. Because of the more limited attention received in the literature when compared to the trend detection on block maxima variables, we perform a Monte Carlo simulation study to evaluate the performance of different approaches: Spearman's rho, Mann–Kendall, ordinary least squares (OLS), Sen's slope estimator (SEN), and the nonstationary generalized Pareto distribution fit to identify the presence of trends in PDS records characterized by different sample sizes (n), shape parameter (ξ) and degrees of nonstationarity. The results point to a power gain for all tests by increasing n and the degree of nonstationarity and by reducing ξ. The use of a nonparametric test is recommended in samples with a high positive skew. Furthermore, the use of sampling rates greater than one to increase the PDS sample size is encouraged, especially when dealing with small records. The use of SEN to estimate the magnitude of a trend is preferable over OLS due to its slightly smaller probability of occurrence of type S error when ξ is positive.

James S. Wheaton, Daniel R. Herber

Traditional requirements engineering tools do not readily access the SysML-defined system architecture model, often resulting in ad-hoc duplication of model elements that lacks the connectivity and expressive detail possible in a SysML-defined model. Further integration of requirements engineering activities with MBSE contributes to the Authoritative Source of Truth while facilitating deep access to system architecture model elements for V&V activities. We explore the application of MBSE to requirements engineering by extending the Model-Based Structured Requirement SysML Profile to comply with the INCOSE Guide to Writing Requirements while conforming to the ISO/IEC/IEEE 29148 standard requirement statement patterns. Rules, Characteristics, and Attributes were defined in SysML according to the Guide to facilitate requirements definition, verification & validation. The resulting SysML Profile was applied in two system architecture models at NASA Jet Propulsion Laboratory, allowing us to assess its applicability and value in real-world project environments. Initial results indicate that INCOSE-derived Model-Based Structured Requirements may rapidly improve requirement expression quality while complementing the NASA Systems Engineering Handbook checklist and guidance, but typical requirement management activities still have challenges related to automation and support in the system architecture modeling software.

Benjamin Decardi-Nelson, Abdulelah S. Alshehri, Akshay Ajagekar et al.

This article explores how emerging generative artificial intelligence (GenAI) models, such as large language models (LLMs), can enhance solution methodologies within process systems engineering (PSE). These cutting-edge GenAI models, particularly foundation models (FMs), which are pre-trained on extensive, general-purpose datasets, offer versatile adaptability for a broad range of tasks, including responding to queries, image generation, and complex decision-making. Given the close relationship between advancements in PSE and developments in computing and systems technologies, exploring the synergy between GenAI and PSE is essential. We begin our discussion with a compact overview of both classic and emerging GenAI models, including FMs, and then dive into their applications within key PSE domains: synthesis and design, optimization and integration, and process monitoring and control. In each domain, we explore how GenAI models could potentially advance PSE methodologies, providing insights and prospects for each area. Furthermore, the article identifies and discusses potential challenges in fully leveraging GenAI within PSE, including multiscale modeling, data requirements, evaluation metrics and benchmarks, and trust and safety, thereby deepening the discourse on effective GenAI integration into systems analysis, design, optimization, operations, monitoring, and control. This paper provides a guide for future research focused on the applications of emerging GenAI in PSE.

Hamidreza Abbaszadeh, Reza Norouzi, Veli Süme et al.

This study investigates the potential of Adaptive Neuro-fuzzy inference system (ANFIS), M5P, and Gaussian Process regression (GP) approaches to predict discharge coefficient (Cd) of chimney weir with different apex angles. Out of 110 data points, 77 arbitrarily selected observations were used for training, whereas the remaining 77 data points were used for testing. Input data consisted of h/p, y/p, L/p, and w/z, whereas Cd was an output. Four shapes of membership functions, i.e., triangular, trapezoidal, generalized bell-shaped, and Gaussian, were used for the ANFIS-based model development. Five different goodness-of-fit parameters and various graphical presentations were used to evaluate the performance of the machine-learning models. It was found that the M5P-based model was superior to other implemented models in predicting the Cd with Correlation Coefficient (CC) (0.9532 and 0.9472), Mean Absolute Error (MAE) (0.0024 and 0.0026), (Root Mean Square Error) RMSE (0.0032 and 0.0033), Scattering Index (SI) (0.0048 and 0.0050), and Nash Sutcliffe Efficiency (NSE) (0.9085 and 0.9925) values in the training and testing stages, respectively. Another major outcome of this study was that the ANFIS model was better than GP and other MFs-based ANFIS-ti models. The sensitivity of the Cd variables is also investigated, which showed h/p and L/p as major influencing factors in the Cd.

Andy Zou, Long Phan, Sarah Chen et al.

In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representations, rather than neurons or circuits, at the center of analysis, equipping us with novel methods for monitoring and manipulating high-level cognitive phenomena in deep neural networks (DNNs). We provide baselines and an initial analysis of RepE techniques, showing that they offer simple yet effective solutions for improving our understanding and control of large language models. We showcase how these methods can provide traction on a wide range of safety-relevant problems, including honesty, harmlessness, power-seeking, and more, demonstrating the promise of top-down transparency research. We hope that this work catalyzes further exploration of RepE and fosters advancements in the transparency and safety of AI systems.

Daniel Badawi, Eduardo Gildin

Physics-Informed machine learning models have recently emerged with some interesting and unique features that can be applied to reservoir engineering. In particular, physics-informed neural networks (PINN) leverage the fact that neural networks are a type of universal function approximators that can embed the knowledge of any physical laws that govern a given data-set in the learning process, and can be described by partial differential equations. The transient diffusivity equation is a fundamental equation in reservoir engineering and the general solution to this equation forms the basis for Pressure Transient Analysis (PTA). The diffusivity equation is derived by combining three physical principles, the continuity equation, Darcy's equation, and the equation of state for a slightly compressible liquid. Obtaining general solutions to this equation is imperative to understand flow regimes in porous media. Analytical solutions of the transient diffusivity equation are usually hard to obtain due to the stiff nature of the equation caused by the steep gradients of the pressure near the well. In this work we apply physics-informed neural networks to the one and two dimensional diffusivity equation and demonstrate that decomposing the space domain into very few subdomains can overcome the stiffness problem of the equation. Additionally, we demonstrate that the inverse capabilities of PINNs can estimate missing physics such as permeability and distance from sealing boundary similar to buildup tests without shutting in the well.

P. Jamwal, Anjali Raj, Lakshmi Raveendran et al.

Abstract Constructed wetlands are a nature-based engineering solution enabling polishing of septic tank effluents at low-cost. However to date, the influence of planting on treatment efficiency remains little understood. Here we report a case study evaluating the performance of two near-identical Horizontal Sub-Surface Flow Constructed Wetlands (HSSF-CW) deployed at a school in southern India. The HSSF-CWs were of similar size and construction with the exception that one system was planted (Canna indica) whilst the other was operated without plants. Both systems were operated at similar hydraulic loading rate (HLR) and hydraulic retention time (HRT) of 84 mm day−1 and 3.7 days, respectively to treat the effluent from septic tanks. The systems were monitored fortnightly for one year and the performance kinetics, nutrient and organics removal efficiencies were evaluated. Significant reduction in biochemical oxygen demand (BOD5) and chemical oxygen demand (COD) (p

Wanrui Wang, Yaning Chen, Yapeng Chen et al.

Intense anthropogenic activities in arid areas have great impacts on groundwater process by causing river dried-up and phreatic decline. Groundwater recharge and discharge have become hot spot in the dried-up river oases of arid regions, but are not well known, challenging water and ecological security. This study applied a stable isotope and end-member mixing analysis method to quantify shallow groundwater sources and interpret groundwater processes using data from 186 water samples in the Wei-Ku Oasis of central Asia. Results showed that shallow groundwater (well depth < 20 m) was mainly supplied by surface water and lateral groundwater flow from upstream, accounting for 88 and 12%, respectively, implying surface water was the dominant source. Stable isotopes and TDS showed obviously spatiotemporal dynamic. Shallow groundwater TDS increased from northwest to southeast, while the spatial variation trend of groundwater δ18O was not obvious. Surface water and groundwater in non-flood season had higher values of stable isotopes and TDS than those in flood season. Anthropogenic activities greatly affect groundwater dynamics, where land-cover change and groundwater overexploitation are the main driving factors. The findings would be useful for further understanding groundwater sources and cycling, and help restore groundwater level and desert ecosystem in the arid region. HIGHLIGHTS The sources of shallow groundwater in the dried-up river oasis of central Asia were quantified.; Surface water was the dominant source of shallow groundwater.; Anthropogenic activities greatly affect groundwater dynamic and cycle.;

Aljosha Köcher, Alexander Hayward, Alexander Fay

Today's production systems are complex networks of cyber-physical systems which combine mechanical and electronic parts with software and networking capabilities. To the inherent complexity of such systems additional complexity arises from the context in which these systems operate. Manufacturing companies need to be able to adapt their production to ever changing customer demands as well as decreasing lot sizes. Engineering such systems, which need to be combined and reconfigured into different networks under changing conditions, requires engineering methods to carefully design them for possible future uses. Such engineering methods need to preserve the flexibility of functions into runtime, so that reconfiguring machines can be done with as little effort as possible. In this paper we present a model-based approach that is focused on machine functions and allows to methodically develop system functionalities for changing system networks. These functions are implemented as so-called skills using automated code-generation.

Gaspare Da Fies, Martin Dutko, Daniel Peck

The homogenisation of the fracture toughness is considered in the context of a propagating hydraulic fracture. The radial (penny-shape) model is utilized, in order to incorporate the impact of the viscosity-toughness regime transition over time. A homogenisation strategy based upon temporal-averaging is investigated. This approach incorporates the instantaneous fracture velocity, meaning that it should remain effective in the case of step-wise crack advancement. The effectiveness of the approach is demonstrated for periodic toughness distributions, including those which are unbalanced, utilizing a highly accurate solver.

Gopi Krishnan Rajbahadur, Shaowei Wang, Yasutaka Kamei et al.

Researchers usually discretize a continuous dependent variable into two target classes by introducing an artificial discretization threshold (e.g., median). However, such discretization may introduce noise (i.e., discretization noise) due to ambiguous class loyalty of data points that are close to the artificial threshold. Previous studies do not provide a clear directive on the impact of discretization noise on the classifiers and how to handle such noise. In this paper, we propose a framework to help researchers and practitioners systematically estimate the impact of discretization noise on classifiers in terms of its impact on various performance measures and the interpretation of classifiers. Through a case study of 7 software engineering datasets, we find that: 1) discretization noise affects the different performance measures of a classifier differently for different datasets; 2) Though the interpretation of the classifiers are impacted by the discretization noise on the whole, the top 3 most important features are not affected by the discretization noise. Therefore, we suggest that practitioners and researchers use our framework to understand the impact of discretization noise on the performance of their built classifiers and estimate the exact amount of discretization noise to be discarded from the dataset to avoid the negative impact of such noise.

Q. Zhai, H. Rahardjo, A. Satyanaga et al.