Hasil untuk "Mining engineering. Metallurgy"

Paul Kobialka, Andrea Pferscher, Bernhard K. Aichernig et al.

With the servitization of business, understanding how users experience services becomes a crucial success factor for companies. Therefore, there is a need to include feedback from user experiences in the software engineering process. Behavioral models of user journeys, describing how users experience their interaction with a service, can provide insights and potentially improve services. In this paper, we investigate techniques that allow the automatic generation of behavioral models from user interactions with a service, recorded in an event log. We first compare two established techniques that generate behavioral models from a given event log: automata learning and process mining. Afterward, we present a novel, hybrid method that combines both automata learning and process mining methods to overcome their limitations. For the existing techniques, we present methods to learn models of user journeys and evaluate the accuracy of the resulting models. We then compare these techniques with our novel method for the automatic extraction of user journey models from the event logs of digital services. We assess the practical applicability of all techniques by evaluating real-world applications. Our results show that process mining techniques rely on expert knowledge, while automata learning techniques depend on the distribution of events in the given event log. We further show that the proposed hybrid technique combines the strengths of both process mining and automata learning, automatically selecting the best method and parameter settings for a given event log to learn very accurate models.

ZHANG Qilong, ZHOU Bing, WANG Guoqiang et al.

Real-time acquisition of global airflow parameters is a key technology for the intelligent control of the ventilation system in metal mines. Currently, AI-based prediction methods for airflow parameters are limited by data dependency, computational costs, and adaptability to different operating conditions. To address this issue, an intelligent perception method for global airflow parameters suitable for metal mines was proposed. First, a wind speed measurement device was used to monitor the average airflow velocity in the roadways in real-time. Monitoring points were strategically arranged, and an airflow parameter monitoring system was established to obtain key ventilation parameters such as air volume and air pressure. Then, based on the actual conditions of the ventilation system and a three-dimensional schematic diagram, a three-dimensional simulation system was developed and optimized using actual measured airflow data. The system simulated the airflow parameters of the mine under different fan operating conditions and natural wind pressure states. Next, based on the simulation data, a training and testing dataset for the AI algorithm model was constructed. Finally, the airflow information collected by the airflow parameter monitoring system was used as input for the AI algorithm model, enabling real-time perception of the global airflow distribution in the mine. Performance evaluation of the intelligent perception model was conducted using ventilation network calculation data. The results showed: ① the model's coefficient of determination (R2) was 0.998, the root mean square error was 0.215 9, the mean absolute error was 0.085, and the mean absolute percentage error was 1.89%. ② The model's predicted values closely aligned with the actual observed values, verifying the excellent performance of the multilayer perceptron (MLP) in airflow parameter prediction. ③ The model maintained its prediction accuracy when faced with different datasets, demonstrating good generalization ability. ④ The average error of the intelligent ventilation system's perception data was controlled within 5%, and the perceived underground airflow parameters were in close agreement with the actual measured values.

Igor A. Melnik

Polymodality of statistical sand grain size distribution is due to the changes in kinematic energy of aquatic environment during the process of sediment deposition in open system-facies. Improving relevance of information about deposition paleoenvironment is of high significance in interpretation of granulometric analysis results. The paper investigates the results of granulometric analysis of sandy-aleuritic deposits confined to different formations in the wells located in the oil fields on the Yamal Peninsula. Based on the kinematic theory of open system transformation, the equation that describes the dependence of grain size on grain kinematic parameters – time period and transport distance – was developed. Therefore, it is possible to calculate these parameters within the studied facies on the basis of available grain sizes and percentage of fraction with diameter range from 0.001 to 1 mm. The aim of this study is to present a new approach to facies identification based on the calculations of kinematic parameters of sand grain flow and fine grains using the equations of open system transformation intensity within the universal kinematic theory. The parameter which was proved the most informative is sediment transport distance during deposition, which is controlled by the size of the settling grains. This parameter is influenced by bed slope angle, grain size, and deposition depth. Comparing the value of this parameter with fraction diameter, it is possible to identify the facies of the studied area.

Zhong Li, Yuzhou Chen, Qiang Guo et al.

Selecting appropriate materials is crucial for mitigating the severe economic and safety challenges posed by microbiologically induced corrosion (MIC) in marine and industrial settings. This study focuses on the MIC behavior of 316L austenitic stainless steel and 2205 duplex stainless steel that is caused by the metabolic activities of <i>D. vulgaris</i> during a life span of 7 days. Cell counts, weight loss, electrochemical measurements, and surface characterization were employed to evaluate the materials’ resistance to MIC. Specifically, 2205 DSS exhibited a 60% lower weight loss (0.02 vs. 0.05 mg/cm²), a 42% lower maximum pit depth (2.11 vs. 3.64 μm), and an orders-of-magnitude lower corrosion current density (0.094 vs. 2.0 μA cm⁻²) compared to 316L SS, demonstrating its superior resistance to <i>D. vulgaris</i> MIC. XRD and XPS analyses revealed that although FeS formed on both materials, FeS₂—a thermodynamically stable deep-sulfidation product—was only present on 316L, indicating a more advanced corrosion stage. The absence of FeS₂ on 2205 suggests limited sulfide corrosion progression. These findings confirm the advantage of duplex stainless steel in mitigating <i>D. vulgaris</i>-induced corrosion and provide insights into the selection of materials for MIC-prone environments.

Cui-ju Wang, Jin-Kai Zhang, Kai-bo Nie et al.

To obtain the Tip with different aspect ratios, the Tip/Mg-5Zn-0.3Ca composite prepared by semi-solid stir casting was subjected to extrusion at 220℃, 180℃, and 140℃, respectively. Then, the effect of the Tip’s aspect ratio on the microstructure, mechanical properties, work hardening and softening behaviors of Tip/Mg-5Zn-0.3Ca composites was investigated. The results indicated that the Tip could be elongated obviously after low-temperature extrusion, and the aspect ratio of which would reach to 13.7:1 as the extrusion temperature deceased to 140℃. Then the “Ti/Mg” layer-like structure was formed in the Tip/Mg-5Zn-0.3Ca composite. Accompanied with the elongation of Tip, the dynamic recrystallized grains and dynamic precipitates were both refined significantly, however, the dynamic recrystallization rate changed a little. The elongated Tip endowed the Tip/Mg-5Zn-0.3Ca composites with better matching of strength and toughness without the sacrifice of elongation and bending strain. Both the work hardening rate and softening rate of Tip/Mg-5Zn-0.3Ca composites increased with the increasing aspect ratio of Tip. The formation of “Ti/Mg” layer-like structure contributed to the redistribution of strain from large aggregations to a network-like distribution, which effectively suppresses the initiation and propagation of micro-cracks, thus enhancing the plasticity of the Tip/Mg-5Zn-0.3Ca composites.

Jayashree Samantray, Amit Anand

Md Rayhanur Rahman, Brandon Wroblewski, Quinn Matthews et al.

Defending from cyberattacks requires practitioners to operate on high-level adversary behavior. Cyberthreat intelligence (CTI) reports on past cyberattack incidents describe the chain of malicious actions with respect to time. To avoid repeating cyberattack incidents, practitioners must proactively identify and defend against recurring chain of actions - which we refer to as temporal attack patterns. Automatically mining the patterns among actions provides structured and actionable information on the adversary behavior of past cyberattacks. The goal of this paper is to aid security practitioners in prioritizing and proactive defense against cyberattacks by mining temporal attack patterns from cyberthreat intelligence reports. To this end, we propose ChronoCTI, an automated pipeline for mining temporal attack patterns from cyberthreat intelligence (CTI) reports of past cyberattacks. To construct ChronoCTI, we build the ground truth dataset of temporal attack patterns and apply state-of-the-art large language models, natural language processing, and machine learning techniques. We apply ChronoCTI on a set of 713 CTI reports, where we identify 124 temporal attack patterns - which we categorize into nine pattern categories. We identify that the most prevalent pattern category is to trick victim users into executing malicious code to initiate the attack, followed by bypassing the anti-malware system in the victim network. Based on the observed patterns, we advocate organizations to train users about cybersecurity best practices, introduce immutable operating systems with limited functionalities, and enforce multi-user authentications. Moreover, we advocate practitioners to leverage the automated mining capability of ChronoCTI and design countermeasures against the recurring attack patterns.

Everton Cavalcante, Thais Batista, Flavio Oquendo

Modern systems are increasingly connected and more integrated with other existing systems, giving rise to \textit{systems-of-systems} (SoS). An SoS consists of a set of independent, heterogeneous systems that interact to provide new functionalities and accomplish global missions through emergent behavior manifested at runtime. The distinctive characteristics of SoS, when contrasted to traditional systems, pose significant research challenges within Software Engineering. These challenges motivate the need for a paradigm shift and the exploration of novel approaches for designing, developing, deploying, and evolving these systems. The \textit{International Workshop on Software Engineering for Systems-of-Systems} (SESoS) series started in 2013 to fill a gap in scientific forums addressing SoS from the Software Engineering perspective, becoming the first venue for this purpose. This article presents a study aimed at outlining the evolution and future trajectory of Software Engineering for SoS based on the examination of 57 papers spanning the 11 editions of the SESoS workshop (2013-2023). The study combined scoping review and scientometric analysis methods to categorize and analyze the research contributions concerning temporal and geographic distribution, topics of interest, research methodologies employed, application domains, and research impact. Based on such a comprehensive overview, this article discusses current and future directions in Software Engineering for SoS.

Siddhant Dutta, Iago Leal de Freitas, Pedro Maciel Xavier et al.

Federated Learning (FL) is a decentralized machine learning approach that has gained attention for its potential to enable collaborative model training across clients while protecting data privacy, making it an attractive solution for the chemical industry. This work aims to provide the chemical engineering community with an accessible introduction to the discipline. Supported by a hands-on tutorial and a comprehensive collection of examples, it explores the application of FL in tasks such as manufacturing optimization, multimodal data integration, and drug discovery while addressing the unique challenges of protecting proprietary information and managing distributed datasets. The tutorial was built using key frameworks such as $\texttt{Flower}$ and $\texttt{TensorFlow Federated}$ and was designed to provide chemical engineers with the right tools to adopt FL in their specific needs. We compare the performance of FL against centralized learning across three different datasets relevant to chemical engineering applications, demonstrating that FL will often maintain or improve classification performance, particularly for complex and heterogeneous data. We conclude with an outlook on the open challenges in federated learning to be tackled and current approaches designed to remediate and improve this framework.

E. Azad, H. Yazdani Sarvestani, B. Ashrafi et al.

Ceramic materials, while strong, often lack flexibility and energy absorption. Inspired by tough natural structures like nacre, toughening strategies have shown significant potential in ceramic materials. This study investigates the static and cyclic flexural properties (i.e., energy absorption, stiffness, and strength) of the bioinspired ceramic-polymer composites, particularly concerning the influence of macro and micro patterns. Using a subtractive manufacturing platform enabled by ultra-short pulsed picosecond lasers, we engrave a range of macro and micro patterns onto alumina tiles, mimicking natural armor designs. The composites are then fabricated by stacking laser-engraved tiles with an interlayer of Surlyn®, a commercial monomer. The results demonstrate that the static/cyclic performance and toughening mechanisms are closely linked to the lasered bioinspired surface patterns and stacking sequence. Specific macro architectures and stacking sequences led to significantly increased energy absorption (up to 85%) through mechanisms like crack deflection and plastic deformation of the soft phase. Micro patterns, on the other hand, improved the ceramic's strength (up to 140%) by influencing how the materials interact at the interface. This research not only advances our understanding of bioinspired armor but also paves the way for a new generation of ceramic composites with superior properties, targeting applications in defense (aerospace and vehicle armor) and personal protective equipment (PPE).

Saizhuo Wang, Hang Yuan, Leon Zhou et al.

One of the most important tasks in quantitative investment research is mining new alphas (effective trading signals or factors). Traditional alpha mining methods, either hand-crafted factor synthesizing or algorithmic factor mining (e.g., search with genetic programming), have inherent limitations, especially in implementing the ideas of quants. In this work, we propose a new alpha mining paradigm by introducing human-AI interaction, and a novel prompt engineering algorithmic framework to implement this paradigm by leveraging the power of large language models. Moreover, we develop Alpha-GPT, a new interactive alpha mining system framework that provides a heuristic way to ``understand'' the ideas of quant researchers and outputs creative, insightful, and effective alphas. We demonstrate the effectiveness and advantage of Alpha-GPT via a number of alpha mining experiments.

Fabio Calefato, Luigi Quaranta, Filippo Lanubile et al.

Background. Due to the widespread adoption of Artificial Intelligence (AI) and Machine Learning (ML) for building software applications, companies are struggling to recruit employees with a deep understanding of such technologies. In this scenario, AutoML is soaring as a promising solution to fill the AI/ML skills gap since it promises to automate the building of end-to-end AI/ML pipelines that would normally be engineered by specialized team members. Aims. Despite the growing interest and high expectations, there is a dearth of information about the extent to which AutoML is currently adopted by teams developing AI/ML-enabled systems and how it is perceived by practitioners and researchers. Method. To fill these gaps, in this paper, we present a mixed-method study comprising a benchmark of 12 end-to-end AutoML tools on two SE datasets and a user survey with follow-up interviews to further our understanding of AutoML adoption and perception. Results. We found that AutoML solutions can generate models that outperform those trained and optimized by researchers to perform classification tasks in the SE domain. Also, our findings show that the currently available AutoML solutions do not live up to their names as they do not equally support automation across the stages of the ML development workflow and for all the team members. Conclusions. We derive insights to inform the SE research community on how AutoML can facilitate their activities and tool builders on how to design the next generation of AutoML technologies.

Urszula Jessen, Michal Sroka, Dirk Fahland

This research investigates the application of Large Language Models (LLMs) to augment conversational agents in process mining, aiming to tackle its inherent complexity and diverse skill requirements. While LLM advancements present novel opportunities for conversational process mining, generating efficient outputs is still a hurdle. We propose an innovative approach that amend many issues in existing solutions, informed by prior research on Natural Language Processing (NLP) for conversational agents. Leveraging LLMs, our framework improves both accessibility and agent performance, as demonstrated by experiments on public question and data sets. Our research sets the stage for future explorations into LLMs' role in process mining and concludes with propositions for enhancing LLM memory, implementing real-time user testing, and examining diverse data sets.

Tao Chen, Miqing Li

Configurable software systems can be tuned for better performance. Leveraging on some Pareto optimizers, recent work has shifted from tuning for a single, time-related performance objective to two intrinsically different objectives that assess distinct performance aspects of the system, each with varying aspirations. Before we design better optimizers, a crucial engineering decision to make therein is how to handle the performance requirements with clear aspirations in the tuning process. For this, the community takes two alternative optimization models: either quantifying and incorporating the aspirations into the search objectives that guide the tuning, or not considering the aspirations during the search but purely using them in the later decision-making process only. However, despite being a crucial decision that determines how an optimizer can be designed and tailored, there is a rather limited understanding of which optimization model should be chosen under what particular circumstance, and why. In this paper, we seek to close this gap. Firstly, we do that through a review of over 426 papers in the literature and 14 real-world requirements datasets. Drawing on these, we then conduct a comprehensive empirical study that covers 15 combinations of the state-of-the-art performance requirement patterns, four types of aspiration space, three Pareto optimizers, and eight real-world systems/environments, leading to 1,296 cases of investigation. We found that (1) the realism of aspirations is the key factor that determines whether they should be used to guide the tuning; (2) the given patterns and the position of the realistic aspirations in the objective landscape are less important for the choice, but they do matter to the extents of improvement; (3) the available tuning budget can also influence the choice for unrealistic aspirations but it is insignificant under realistic ones.

Xiao Lu, Liang Zhang, Chen Chen et al.

In this study, Si3N4 nanowires (NWs) with ceramic properties were incorporated into Sn1.0Ag0.5Cu (SAC105) solder to enhance its overall performance. The thermal properties, spreading behavior, microstructure, interface, and mechanical properties of SAC105-xSi3N4 (x = 0, 0.2, 0.4, 0.6, 0.8, 1.0 wt%) solders were systematically investigated. The research revealed that doping Si3N4 NWs into SAC105 solder could expand its melting range and decrease undercooling. Notably, the solder alloy containing 0.6 wt% Si3N4 NWs had the lowest thermal expansion coefficient (CTE), which improved the CTE matching of SAC105 solder with Cu substrate. Although the solder with 0.4 wt% Si3N4 NWs exhibited superior wetting properties, it was less effective in refining the microstructure and interfacial intermetallic compounds (IMC) than those containing 0.6 wt% Si3N4 NWs. Meanwhile, when the β-Sn phase in the matrix and the Cu6Sn5 IMC phase at the interface were analyzed by electron back scatter diffraction (EBSD), their grain orientation was found to be optimized by the doping of 0.6 wt% Si3N4 NWs. The <001> direction of the β-Sn grains of SAC105-0.6Si3N4 was perpendicular to the Cu substrate, showing a texture structure. The grain orientation of the interfacial Cu6Sn5 IMC made it well-adapted for three-dimensional (3D) packaging. Finally, the mechanical properties enhancement of the solder joints were analyzed in detail by combining the fracture morphology and the EBSD results of the Sn matrix.

Dongqun Xin, Xiucong Yao, Jian Zhang et al.

Functionally graded materials (FGMs) are novel composite materials characterized by gradual changes in compositions and/or microstructures along at least one direction and hence locally tailored properties. In this paper, an innovative twin-wire plasma arc additive manufacturing (TW-PAAM) process was used to fabricate the thin-walled stainless steel 304 L/Inconel625 compositionally graded materials. The chemical composition, microstructure, phases, and microhardness of the as-fabricated FGMs were investigated. The results reveal that sharp changes in composition between 304 L and In625 in non-graded sample resulted in large variations in microstructural morphology and hardness around the interface between these two materials. With the increase of the gradient layers, the microstructural morphology displayed a smooth transition from 304 L to In625. However, cracks were found in the 25%In625 region due to MC carbides distributed at the grain boundary and A solidification mode. The grain growth at the interfaces between adjacent layers with different compositions follows a typical epitaxial growth. As the mixing ratio of In625 increased, the secondary phases changed from MC carbide to Laves phase and their content increased. Furthermore, the microhardness decreased in the 21%In625 region, then increased with the increase in mixing ratio of In625. The absence of δ-ferrite and low content of secondary phases were the main factors contributing to the decrease in microhardness in the 21%625 region. The study provides a guideline for the wire arc additive manufacturing of 304 L/In625 FGMs with the consideration of gradient composition to avoid cracks and weakening of properties.

Jie Wang, Qinjun Yu, Zhuozhi Xiang et al.

To study the influence of the addition of basalt fibers on the mechanical properties, pore structure, and damage evolution characteristics of the cemented tailings backfill (CTB), the uniaxial compression tests, nuclear magnetic resonance tests and scanning electron microscopy analysis were conducted on the CTB with four different content and lengths of basalt fibers. Test results show the following. (1) An increase in the content of basalt fibers will lead to an increase in the proportion of micropores and secondary pores in the CTB, while a decrease in the proportion of macropores. The influence of basalt fiber length on pore structure is not as significant as the content. (2) With the increase of basalt fiber content and length, the peak stress and peak strain of the CTB increase, but the elastic modulus decreases. Basalt fiber can significantly improve the ductility and bearing time of the CTB, with a length of 12 mm and a content of 1.5 % having the best effect. The length of basalt fibers affects macroscopic mechanics more than content. (3) The CTB without fiber have fewer cracks and faster crack propagation speed, while the CTB with fiber have more cracks and slower crack propagation speed. Basalt fibers mainly play a bridging role between hydration products, delaying the failure process of the sample. (4) A damage constitutive model was constructed. The rationality and reliability of the model were verified, and the damage evolution law of CTB was analyzed. The content and length of basalt fibers have a positive impact on damage evolution.

Lichun Jiang, Hao Zhang, Mi Zhou et al.

Zhilu Lai, Wei Liu, Xudong Jian et al.

The order/dimension of models derived on the basis of data is commonly restricted by the number of observations, or in the context of monitored systems, sensing nodes. This is particularly true for structural systems (e.g., civil or mechanical structures), which are typically high-dimensional in nature. In the scope of physics-informed machine learning, this paper proposes a framework -- termed Neural Modal ODEs -- to integrate physics-based modeling with deep learning for modeling the dynamics of monitored and high-dimensional engineered systems. Neural Ordinary Differential Equations -- Neural ODEs are exploited as the deep learning operator. In this initiating exploration, we restrict ourselves to linear or mildly nonlinear systems. We propose an architecture that couples a dynamic version of variational autoencoders with physics-informed Neural ODEs (Pi-Neural ODEs). An encoder, as a part of the autoencoder, learns the abstract mappings from the first few items of observational data to the initial values of the latent variables, which drive the learning of embedded dynamics via physics-informed Neural ODEs, imposing a modal model structure on that latent space. The decoder of the proposed model adopts the eigenmodes derived from an eigen-analysis applied to the linearized portion of a physics-based model: a process implicitly carrying the spatial relationship between degrees-of-freedom (DOFs). The framework is validated on a numerical example, and an experimental dataset of a scaled cable-stayed bridge, where the learned hybrid model is shown to outperform a purely physics-based approach to modeling. We further show the functionality of the proposed scheme within the context of virtual sensing, i.e., the recovery of generalized response quantities in unmeasured DOFs from spatially sparse data.

Yu Zhou, Weilin Zhan, Zi Li et al.

A Dockerfile defines a set of instructions to build Docker images, which can then be instantiated to support containerized applications. Recent studies have revealed a considerable amount of quality issues with Dockerfiles. In this paper, we propose a novel approach DRIVE (Dockerfiles Rule mIning and Violation dEtection) to mine implicit rules and detect potential violations of such rules in Dockerfiles. DRIVE firstly parses Dockerfiles and transforms them to an intermediate representation. It then leverages an efficient sequential pattern mining algorithm to extract potential patterns. With heuristic-based reduction and moderate human intervention, potential rules are identified, which can then be utilized to detect potential violations of Dockerfiles. DRIVE identifies 34 semantic rules and 19 syntactic rules including 9 new semantic rules which have not been reported elsewhere. Extensive experiments on real-world Dockerfiles demonstrate the efficacy of our approach.