Hasil untuk "Mining engineering. Metallurgy"

Sijia YANG, Yuege XIONG, Xiaokun WANG et al.

Visualizing characteristics of blood flow in the human body is essential for accurate diagnosis of cardiovascular diseases, analysis of pathological mechanisms, and optimization of personalized treatment. However, traditional medical methods, relying primarily on imaging observations and empirical analysis, face significant limitations in directly observing blood flow states and lack sufficient quantitative assessment of the coupled effects of blood components. Therefore, in this study, we propose a blood flow characteristics simulation method based on a multicomponent non-Newtonian fluid model, integrating rheological modeling, multiphase coupling, and fluid–solid interaction mechanisms to address these problems. The proposed method takes three pivotal advancements into consideration. First, the Walburn–Schneck model is employed to describe the shear-thinning behavior of non-Newtonian fluids, wherein the viscosity is characterized as a function of shear rate. Second, the Walburn–Schneck model is extended to multicomponent application scenarios by introducing volume fractions, enabling the modeling of interaction mechanisms between different components and their collective influence on bulk viscosity. This extension allows for accurate simulation of multicomponent non-Newtonian fluid dynamics, including the complex deformation and flow patterns that traditional single-component models struggle to capture. Third, a solid–liquid interaction force model at the blood vessel wall is constructed using an improved smoothed particle hydrodynamics framework. The model incorporates wall shear stress and adhesive forces, effectively mitigating computational inaccuracies near the fluid-solid boundary caused by particle truncation. As a result, the model achieves robust simulations in complex vascular geometries. To verify the effectiveness of the proposed method for blood flow simulation, a series of experiments were performed. The drop and deformation experiments of non-Newtonian fluids were first conducted. The results demonstrated that the Walburn–Schneck model can accurately capture the shear rate-dependent viscosity changes, outperforming the Carreau model in reproducing fluid extension and thinning effects. To further assess the model’s adaptability to high-viscosity fluids, experiments on the coiling and folding phenomena exhibited by non-Newtonian fluids with high-viscosity characteristics were also carried out. The extended Walburn–Schneck model effectively captured and maintained the complex crease effects generated by fluid curling and folding, thereby verifying the model’s accuracy and applicability in high-viscosity scenarios. Then, simulations of multicomponent non-Newtonian fluids with varying volume fractions of high-viscosity components were carried out, and the stability of the multicomponent non-Newtonian fluid model was verified through the three-phase dam break experiment. Finally, simulations across diverse vascular scenarios were conducted to verify the efficacy of the solid-liquid interaction force model and the multicomponent non-Newtonian fluid model in the blood flow scenario. The model effectively reproduced mixing-diffusion behaviors in complex vascular structures, including straight, bifurcated, and stenotic vessels. Stable fluid–solid coupling and no particle penetration were observed, highlighting the robustness and accuracy of the proposed method. The research results provide a new technical pathway for digital and intelligent medical diagnosis, holding promise to assist in deepening the understanding of pathological mechanisms related to hemodynamic abnormalities. By integrating the fluid viscosity of the multicomponent with non-Newtonian rheology, the method improves the accuracy of hemodynamic simulations. Future work will focus on integrating microscale cellular interactions and dynamic vascular elasticity to further bridge the gap between simulation and clinical reality.

Ana B. M. Bett, Thais S. Nepomuceno, Edson OliveiraJr et al.

Context: The empirical software engineering (ESE) community has contributed to improving experimentation over the years. However, there is still a lack of rigor in describing controlled experiments, hindering reproducibility and transparency. Registered Reports (RR) have been discussed in the ESE community to address these issues. A RR registers a study's hypotheses, methods, and/or analyses before execution, involving peer review and potential acceptance before data collection. This helps mitigate problematic practices such as p-hacking, publication bias, and inappropriate post hoc analysis. Objective: This paper presents initial results toward establishing an RR template for Software Engineering controlled experiments using the Open Science Framework (OSF). Method: We analyzed templates of selected OSF RR types in light of documentation guidelines for controlled experiments. Results: The observed lack of rigor motivated our investigation of OSF-based RR types. Our analysis showed that, although one of the RR types aligned with many of the documentation suggestions contained in the guidelines, none of them covered the guidelines comprehensively. The study also highlights limitations in OSF RR template customization. Conclusion: Despite progress in ESE, planning and documenting experiments still lack rigor, compromising reproducibility. Adopting OSF-based RRs is proposed. However, no currently available RR type fully satisfies the guidelines. Establishing RR-specific guidelines for SE is deemed essential.

Mariana Alvarenga Alves, Eduarda Machado Rodrigues, Luiz Alberto Oliveira Rocha et al.

Thin steel plates with stiffeners are widely used in shipbuilding, aeronautics, and civil construction due to their lightness and structural strength. This study presents a numerical model developed using ANSYS Mechanical APDL with SHELL281 finite elements to evaluate the deflection of thin steel plates with trapezoidal-shaped box-beam stiffeners, known as hat-stiffened plates. The structure is analyzed under a uniformly distributed load perpendicular to the plate, with simply supported boundary conditions. The constructal design method combined with the exhaustive search technique is employed to optimize the geometry. A volume fraction of 30% is used, transferring material from the reference plate (without stiffeners) to the stiffeners, defining parameters such as number, height, and thickness—considered degrees of freedom. The stiffener angle is fixed at 120°. The results show that increasing stiffener height and reducing thickness generally improve structural performance by reducing deflections. The best configuration with transverse stiffeners reduced deflection by 97.15% compared to the reference plate, and by 79.27% compared to the best longitudinal configuration from previous studies. Therefore, transverse stiffeners were more effective than longitudinal ones. This study highlights the importance of stiffener orientation and geometry in the structural optimization of thin steel plates.

Egor A. Knyazkin, Dmitrii A. Klebanov, Roman O. Yuvakaev

This article examines the problem of managing ore flow quality at mining enterprises from the perspective of applying big data to improve the efficiency of mineral quality management. It is noted that assessing the feasibility of collecting and processing big data for ore flow quality control requires an optimal quantifiable weight parameter, which determines the data collection discreteness and the effectiveness of their processing. Currently, this parameter is the ore (or concentrate) batch. A scientific-practical approach to determining batch sizes at mining enterprises is proposed, based not on business process conditions, but on the analysis of the distribution of quality parameters within the ore body, considering subsequent methods of mineral raw material transportation. An analysis was conducted on the data from every technological process within the mining technical system, leading to the establishment of principles for calculating the minimum required data samples for each stage of the process. The applicability of the Kotelnikov theorem (Nyquist – Shannon sampling theorem) for determining the optimal quantifiable weight parameter of a mineral raw material batch within quality control frameworks is considered. To obtain a qualitative model, the required scope of quarry operation statistics should range from 16 to 52 months of excavator operation at the face. This range depends on the value of the mineral quality distribution coefficient at the mining enterprise. It was also established that for building a qualitative model, the mentioned coefficient must be considered; the higher its value, the lower the sampling frequency should be when collecting data from technological processing stages.

Rahul Kumar, Kamlesh Sahoo, Manish Kumar Singh et al.

Developing bulk high entropy alloys (HEAs) with good strength and ductility combinations is challenging. Many of the currently reported HEAs are prepared from pure metals. The current study selected a multicomponent CoCrFeMn alloy and prepared it using scrap, ferroalloys, and pure elements. Further improvement in the properties of as-cast alloys is done by minute solute addition. The Thermo-Calc® simulation studies identified the maximum amount of minute solute elements that can be added without any new phase formation. The studied master alloy and modified compositions show a multiphase structure with FCC and HCP phases. The detailed microstructural analysis confirms that the secondary dendritic arm spacing was reduced while adding trace elements, and Cu-containing alloys showed a reduction of ∼44.44 %. The effect of the casting condition was studied by varying the heat transfer condition via different mould geometries. The mechanical properties, such as the tensile test and Vickers microhardness, show remarkable improvement with minute additions of solutes and by varying heat transfer conditions. The master alloy and Cu containing alloy show a maximum strength of ∼429 MPa and ∼562 MPa, respectively. The Cu-containing alloy shows an outstanding strength-ductility combination, and the detailed TEM-STEM analysis confirms the formation of Fe-rich clusters and Cu-rich phases. The current study shows a cost reduction of ∼1/10 compared with the alloys formed by pure elements.

Mattia Merlin, Lorenzo Antonioli, Federico Bin et al.

Foundry aluminum-silicon (Al-Si) alloys, especially those containing Cu and/or Mg, are widely used in casting processes for fabricating lightweight parts. This study focuses on the optimization of the solution heat treatment parameters within the T6 heat treatment of an innovative AlSi7Cu0.5Mg0.3 secondary alloy, aiming at achieving energy savings and reducing the environmental impact related to the production of foundry components for the automotive industry. Different combinations of solution times and temperatures lower than those typically adopted in industrial practice were evaluated, and their effects on tensile properties were investigated on samples machined from as-cast and T6-treated castings produced by pouring the alloy into a steel permanent mold. Thermal analysis (TA) and differential thermal analysis (DTA) were performed to monitor the solidification sequence of microstructural phases as well as their dissolution on heating according to the proposed solution heat treatments. Microstructural analysis by light microscopy (LM) and scanning electron microscopy (SEM), together with Brinell hardness testing, was also carried out to assess the effects of heat treatment parameters. The results suggested that a shorter solution heat treatment set at a temperature lower than that currently adopted for the heat treatment of the studied alloy can still ensure the required mechanical properties while improving productivity and reducing energy consumption.

Yimeng WANG, Na LI, Xueer HE et al.

In this article, vanadium is extracted from a vanadium-bearing stone coal in Shanyang by the process of melt-roasting-water leaching. The experimental roasting and leaching conditions were optimized, including sodium peroxide dosage, roasting time, roasting temperature, leaching method and ash treatment. The results showed that the leaching rate of vanadium was maximum when the dosage of sample and sodium peroxide was 1∶3, roasting temperature was 700 ℃ and roasting time was 7 min. The concentrations of vanadium in the leaching solution were found to be 1.38 mg/L in the leaching samples at the optimum working conditions.

Martin Obaidi, Marc Herrmann, Jil Klünder et al.

Software development relies heavily on text-based communication, making sentiment analysis a valuable tool for understanding team dynamics and supporting trustworthy AI-driven analytics in requirements engineering. However, existing sentiment analysis tools often perform inconsistently across datasets from different platforms, due to variations in communication style and content. In this study, we analyze linguistic and statistical features of 10 developer communication datasets from five platforms and evaluate the performance of 14 sentiment analysis tools. Based on these results, we propose a mapping approach and questionnaire that recommends suitable sentiment analysis tools for new datasets, using their characteristic features as input. Our results show that dataset characteristics can be leveraged to improve tool selection, as platforms differ substantially in both linguistic and statistical properties. While transformer-based models such as SetFit and RoBERTa consistently achieve strong results, tool effectiveness remains context-dependent. Our approach supports researchers and practitioners in selecting trustworthy tools for sentiment analysis in software engineering, while highlighting the need for ongoing evaluation as communication contexts evolve.

Dehai Zhao, Zhenchang Xing, Qinghua Lu et al.

UI automation is a useful technique for UI testing, bug reproduction, and robotic process automation. Recording user actions with an application assists rapid development of UI automation scripts, but existing recording techniques are intrusive, rely on OS or GUI framework accessibility support, or assume specific app implementations. Reverse engineering user actions from screencasts is non-intrusive, but a key reverse-engineering step is currently missing - recognizing human-understandable structured user actions ([command] [widget] [location]) from action screencasts. To fill the gap, we propose a deep learning-based computer vision model that can recognize 11 commands and 11 widgets, and generate location phrases from action screencasts, through joint learning and multi-task learning. We label a large dataset with 7260 video-action pairs, which record user interactions with Word, Zoom, Firefox, Photoshop, and Windows 10 Settings. Through extensive experiments, we confirm the effectiveness and generality of our model, and demonstrate the usefulness of a screencast-to-action-script tool built upon our model for bug reproduction.

Maryam Khan, Muhammad Azeem Akbar, Jussi Kasurinen

Context: Large Language Models (LLMs) such as ChatGPT are increasingly adopted in software engineering (SE) education, offering both opportunities and challenges. Their adoption requires systematic investigation to ensure responsible integration into curricula. Objective: This doctoral research aims to develop a validated framework for integrating LLMs into SE education through a multi-phase process, including taxonomies development, empirical investigation, and case studies. This paper presents the first empirical step. Method: We conducted a pilot repository mining study of 400 GitHub projects, analyzing README files and issues discussions to identify the presence of motivator and demotivator previously synthesized in our literature review [ 8] study. Results: Motivators such as engagement and motivation (227 hits), software engineering process understanding (133 hits), and programming assistance and debugging support (97 hits) were strongly represented. Demotivators, including plagiarism and IP concerns (385 hits), security, privacy and data integrity (87 hits), and over-reliance on AI in learning (39 hits), also appeared prominently. In contrast, demotivators such as challenges in evaluating learning outcomes and difficulty in curriculum redesign recorded no hits across the repositories. Conclusion: The study provides early empirical validation of motivators/demotivators taxonomies with respect to their themes, highlights research practice gaps, and lays the foundation for developing a comprehensive framework to guide the responsible adoption of LLMs in SE education.

Roham Koohestani, Philippe de Bekker, Begüm Koç et al.

Benchmarks are essential for unified evaluation and reproducibility. The rapid rise of Artificial Intelligence for Software Engineering (AI4SE) has produced numerous benchmarks for tasks such as code generation and bug repair. However, this proliferation has led to major challenges: (1) fragmented knowledge across tasks, (2) difficulty in selecting contextually relevant benchmarks, (3) lack of standardization in benchmark creation, and (4) flaws that limit utility. Addressing these requires a dual approach: systematically mapping existing benchmarks for informed selection and defining unified guidelines for robust, adaptable benchmark development. We conduct a review of 247 studies, identifying 273 AI4SE benchmarks since 2014. We categorize them, analyze limitations, and expose gaps in current practices. Building on these insights, we introduce BenchScout, an extensible semantic search tool for locating suitable benchmarks. BenchScout employs automated clustering with contextual embeddings of benchmark-related studies, followed by dimensionality reduction. In a user study with 22 participants, BenchScout achieved usability, effectiveness, and intuitiveness scores of 4.5, 4.0, and 4.1 out of 5. To improve benchmarking standards, we propose BenchFrame, a unified framework for enhancing benchmark quality. Applying BenchFrame to HumanEval yielded HumanEvalNext, featuring corrected errors, improved language conversion, higher test coverage, and greater difficulty. Evaluating 10 state-of-the-art code models on HumanEval, HumanEvalPlus, and HumanEvalNext revealed average pass-at-1 drops of 31.22% and 19.94%, respectively, underscoring the need for continuous benchmark refinement. We further examine BenchFrame's scalability through an agentic pipeline and confirm its generalizability on the MBPP dataset. All review data, user study materials, and enhanced benchmarks are publicly released.

Paloma Guenes, Rafael Tomaz, Bianca Trinkenreich et al.

Research shows that more than half of software professionals experience the Impostor Phenomenon (IP), with a notably higher prevalence among women compared to men. IP can lead to mental health consequences, such as depression and burnout, which can significantly impact personal well-being and software professionals' productivity. This study investigates how IP manifests among software professionals across intersections of gender with race/ethnicity, marital status, number of children, age, and professional experience. Additionally, it examines the well-being of software professionals experiencing IP, providing insights into the interplay between these factors. We analyzed data collected through a theory-driven survey (n = 624) that used validated psychometric instruments to measure IP and well-being in software engineering professionals. We explored the prevalence of IP in the intersections of interest. Additionally, we applied bootstrapping to characterize well-being within our field and statistically tested whether professionals of different genders suffering from IP have lower well-being. The results show that IP occurs more frequently in women and that the prevalence is particularly high among black women as well as among single and childless women. Furthermore, regardless of gender, software engineering professionals suffering from IP have significantly lower well-being. Our findings indicate that effective IP mitigation strategies are needed to improve the well-being of software professionals. Mitigating IP would have particularly positive effects on the well-being of women, who are more frequently affected by IP.

Сергій Орищенко, Віктор Орищенко

Під час робочого процесу навантажувач перемішується на майже горизонтальних майданчиках, допустимий ухил яких. Розрахунок поздовжньої стійкості навантажувачів ведеться з умови перекидання вперед з урахуванням того, що деформуються пневматичні шини, якщо пневмоколісний хід. Кут додаткового нахилу навантажувача вперед внаслідок деформації опор визначається співвідношенням сили тяжкості навантажувача з вантажем жорсткість ґрунту під переднім та заднім котками гусеничного ходу або радіальна жорсткість передніх та задніх пневматичних шин навантажувача на пневмоколісному ході; відстань між центром ваги навантажувача та вертикальною віссю, що проходить через точку перекидання. Тому при розрахунку поздовжньої стійкості гусеничного та пневмоколісного навантажувачів. Найменший запас поздовжньої стійкості має навантажувач у разі руху під ухил з одночасним гальмуванням машини та робочого обладнання при його опусканні. Положення робочого обладнання відповідає максимальному вильоту.

E. Merino, S. Cere, A. Duran et al.

The aim of this work is to develop a glass-like CexOy coating to seal the pores of a Flash-PEO coated AZ31B Mg alloy and simultaneously provide smart self-healing corrosion protection. The cerium sol was synthesized using cerium acetate as main precursor by sol-gel method. SEM micrographs revealed that upon cerium sol deposition, the pores of the oxide coating were effectively sealed, resulting in a double-layer coating system and thereby in a big reservoir of cerium ions (Ce3+/Ce4+). The glassy character of the cerium coating, confirmed by X-Ray diffraction, implies that cerium exists in Ce3+ and Ce4+ ionic states enclosed in a high internal energy structure which facilitate the diffusion of cerium ions to active cathodic zone. Electrochemical Impedance Spectroscopy (EIS), X-Ray Diffraction (XRD), and Raman spectroscopy were used to explore the active corrosion protection of the CexOy sol-gel coating. The corrosion inhibition mechanism involves the migration of cerium ions and the precipitation of insoluble-crystalline cerium compounds (CeO2). The coating demonstrated self-healing properties, presenting a promising alternative to traditional chrome conversion coatings (CCC).

Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais et al.

Graphical User Interfaces (GUIs) are central to app development projects. App developers may use the GUIs of other apps as a means of requirements refinement and rapid prototyping or as a source of inspiration for designing and improving their own apps. Recent research has thus suggested retrieving relevant GUI designs that match a certain text query from screenshot datasets acquired through crowdsourced or automated exploration of GUIs. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements, neglecting visual information such as icons or background images. In addition, retrieved screenshots are not steered by app developers and lack app features that require particular input data. To overcome these limitations, this paper proposes GUing, a GUI search engine based on a vision-language model called GUIClip, which we trained specifically for the problem of designing app GUIs. For this, we first collected from Google Play app introduction images which display the most representative screenshots and are often captioned (i.e.~labelled) by app vendors. Then, we developed an automated pipeline to classify, crop, and extract the captions from these images. This resulted in a large dataset which we share with this paper: including 303k app screenshots, out of which 135k have captions. We used this dataset to train a novel vision-language model, which is, to the best of our knowledge, the first of its kind for GUI retrieval. We evaluated our approach on various datasets from related work and in a manual experiment. The results demonstrate that our model outperforms previous approaches in text-to-GUI retrieval achieving a Recall@10 of up to 0.69 and a HIT@10 of 0.91. We also explored the performance of GUIClip for other GUI tasks including GUI classification and sketch-to-GUI retrieval with encouraging results.

Marvin Wyrich, Marvin Muñoz Barón, Justus Bogner

Software engineering (SE) is full of abstract concepts that are crucial for both researchers and practitioners, such as programming experience, team productivity, code comprehension, and system security. Secondary studies aimed at summarizing research on the influences and consequences of such concepts would therefore be of great value. However, the inability to measure abstract concepts directly poses a challenge for secondary studies: primary studies in SE can operationalize such concepts in many ways. Standardized measurement instruments are rarely available, and even if they are, many researchers do not use them or do not even provide a definition for the studied concept. SE researchers conducting secondary studies therefore have to decide a) which primary studies intended to measure the same construct, and b) how to compare and aggregate vastly different measurements for the same construct. In this experience report, we discuss the challenge of study selection in SE secondary research on latent variables. We report on two instances where we found it particularly challenging to decide which primary studies should be included for comparison and synthesis, so as not to end up comparing apples with oranges. Our report aims to spark a conversation about developing strategies to address this issue systematically and pave the way for more efficient and rigorous secondary studies in software engineering.

Xin Wang, Quanle Zou, Ying Liu et al.

Cementing technology can effectively extend the life of coalbed methane surface drilling. The fluidity of the cement slurry during cementing is critical to the cementing quality. It is an effective way to improve the cementing quality by increasing the fluidity and pumping efficiency of cement paste by adding dispersants. In this paper, the effect of naphthalene dispersant on the hydration kinetics of G-grade cement was investigated by nuclear magnetic resonance. The results show that the increase of naphthalene dispersant mass fraction can effectively slow down the hydration of cement. The first relaxation peak of cement is correlated with its mobility, and the calculation of its peak index, area size, area share and combined action factor can be used to evaluate the retarding and dispersing effect of naphthalene dispersant on cement slurry more accurately. The main effects of naphthalene dispersant retarding and dispersing are: naphthalene dispersant causes an increase in ξ potential of cement particles, which makes the potential barrier overcome by cement particle coalescence rise; the sulfonic acid group of naphthalene dispersant can form a more stable complex with Ca2+, resulting in a reduced hydration rate. Naphthalene dispersant can decompose in cement into anions adsorbed on the surface of cement particles, forming a solvation film and producing a lubricating and dragging effect. The obtained research results provide theoretical support for the preparation and pumping of on-site cementing slurry from three aspects: the fluidity of the naphthalene dispersant modified cement slurry, the retarding effect and how to choose the pumping period.

Zhiyu Fan, Yannic Noller, Ashish Dandekar et al.

The growing number of students enrolling in Computer Science (CS) programmes is pushing CS educators to their limits. This poses significant challenges to computing education, particularly the teaching of introductory programming and advanced software engineering (SE) courses. First-year programming courses often face overwhelming enrollments, including interdisciplinary students who are not CS majors. The high teacher-to-student ratio makes it challenging to provide timely and high-quality feedback. Meanwhile, software engineering education comes with inherent difficulties like acquiring industry partners and the dilemma that such software projects are often under or over-specified and one-time efforts within one team or one course. To address these challenges, we designed a novel foundational SE course. This SE course envisions building a full-fledged Intelligent Tutoring System (ITS) of Programming Assignments to provide automated, real-time feedback for novice students in programming courses over multiple years. Each year, SE students contribute to specific short-running SE projects that improve the existing ITS implementation, while at the same time, we can deploy the ITS for usage by students for learning programming. This project setup builds awareness among SE students about their contribution to a "to-be-deployed" software project. In this multi-year teaching effort, we have incrementally built an ITS that is now deployed in various programming courses. This paper discusses the Intelligent Tutoring System architecture, our teaching concept in the SE course, our experience with the built ITS, and our view of future computing education.

Alejandro Cruz Ramírez, Eduardo Colin García, José Federico Chávez Alcalá et al.

Different processing routes have been developed to increase the strength and hardness of camshafts for automotive applications. In this work, two carbidic austempered ductile irons (CADIs), alloyed with 0.2 and 0.4 wt% Cr, were evaluated to determine their suitability in the camshaft production by microscopy techniques and mechanical tests. The CADIs were produced at austempering temperatures of 265 and 305 °C, during 30, 60, 90, and 120 min. The microstructural characterization was carried out by optical microscopy, while Rockwell C Hardness, tensile, Charpy impact, and block-on-ring wear loss tests were evaluated for mechanical characterization from the camshaft and standard keel block. The volume fraction of high-carbon austenite was determined for the heat treatment conditions by X-ray diffraction measurements. The process window was found in the range from 60 to 120 min, for both austempering temperatures, while the highest amount of ausferrite was obtained at 90 min. The formation of carbides was increased as the chromium content was increased. The highest hardness (49 HRC) and wear resistance (0.252 mm³) were obtained for the lower austempering temperature (265 °C, 90 min) and higher chromium content (0.4%). The highest austempering temperature (305 °C, 90 min) and lowest chromium content (0.2%) allow for obtaining the highest toughness (22.91 J) and elongation (4.2%), while the highest tensile strength (1027 MPa) was obtained for the CADI containing 0.2% Cr heat-treated to 265 °C.

CHEN Biao, LU Zhaolin, DAI Wei et al.

The existing coal-gangue separation methods based on vision technology have problems of large model parameter amount, poor feature extraction capability and low recognition precision. In order to solve the above problems, a coal-gangue recognition method based on YOLOX-S model combined lightweight Ghost-S network and hybrid parallel attention module (HPAM) named HPG-YOLOS-S model is proposed. Firstly, HPAM is added to the backbone network of YOLOX-S model. Thus the important information in an image is enhanced, and the secondary information is inhibited. The feature extraction capability of the backbone network is enhanced. Secondly, the backbone network of YOLOX-S model is replaced by Ghost-S network with smaller parameter quantity. The utilization rate and feature fusion capability are improved. Finally, in the predection layer, the SIOU loss function is used to replace the loss function of YOLOX-S model to impsrove the detection and positioning precision and enhance the extraction capability of the target. In order to verify the detection effect of the proposed method on large coal-gangue, the HPG-YOLOX-S model is compared with YOLOX-S model. The results show that the identification accuracy of the HPG-YOLOX-S model for coal and gangue is 99.53% and 99.60% respectively, which is 2.51% and 1.27% higher than those of YOLOX-S model. The results of validation show that the precision rate, recall rate and F1 value of the HPG-YOLOX-S model are all above 94%, which are 5.68%, 3.51% and 2.91% higher than those of YOLOX-S model respectively. The parameters amount of the HPG-YOLOX-S model is 7.8 MB, which is 1.2 MB lower than that of YOLOX-S model. The ablation experiment results show that the mean average precision of the HPG-YOLOX-S model is 9.17% higher than that of YOLOX-S model. The experiment result of visualization of the thermodynamic diagram shows that the HPG-YOLOX-S model focuses on the surface differences between coal and gangue, such as texture and contour. The model pays more attention to the overall target of coal-gangue.