Journal of Engineering Research and Reports

AI-Based Architectural, Mechanical, Electrical and Plumbing BIM Object Classification Model and Semantic Enrichment Framework

Enobong Archibong — 2026-03-28

Building Information Modelling (BIM) is increasingly being adopted across the architecture, engineering, and construction industries for digitally simulating and managing infrastructure projects. Despite the growth in BIM utilisation, challenges persist in the classification and semantic enrichment of architectural, mechanical, electrical, and plumbing (MEP) objects, critical components in infrastructure modelling. While some studies have addressed object classification or semantic enrichment independently, there is limited research on integrating both, particularly for MEP components where semantic clarity and interoperability are essential for effective cross-disciplinary stakeholder collaboration. This paper introduces a novel AI-based framework for architectural MEP BIM object classification and semantic enrichment, incorporating multiple deep learning components. The proposed system leverages 3D Convolutional Neural Networks (CNN) for spatial feature extraction, Graph Neural Network Transformers for capturing relational features, and a CNN-based feature fusion model

Design and Numerical Performance Assessment of a Variable-Geometry Two-Body Wave Energy Converter

Anthony A. Adeyanju — 2026-03-28

Wave energy converters (WECs) offer a promising pathway toward diversifying renewable energy portfolios, particularly for coastal and island regions with persistent wave climates. Among existing architectures, two-body WECs are attractive due to their ability to exploit relative motion and multiple degrees of freedom for enhanced energy capture. However, conventional designs often suffer from narrow-band performance and limited adaptability to varying sea states. The objective of this study is to design, numerical modelling, and performance evaluation of a two-body point absorber wave energy converter incorporating a mechanically realizable variable-geometry mechanism. The proposed system consists of a floating body and a submerged body coupled through a direct-drive linear power take-off (PTO), with adjustable float positioning enabled by an ACME power screw and worm-gear actuation. The variable geometry allows controlled modification of hydrostatic stability, restoring moments, and resonance characteristics. Hydrodynamic coefficients were computed using linear boundary element methods in ANSYS AQWA and integrated into WEC-Sim for time-domain simulations under both regular and irregular wave conditions. Structural integrity and fatigue performance were assessed using finite element analysis to ensure survivability under representative operational and extreme sea states. Simulation results demonstrate that float spatial configuration has a pronounced influence on hydrostatic stability, motion response, resonance behaviour, and power absorption efficiency. Among the tested configurations, the intermediate (middle) geometry consistently achieved the most favourable balance between motion amplification and stability, resulting in superior energy capture potential across a wide range of wave periods and heights. The highest configuration provided increased structural safety and reduced fatigue loading, while the lowest configuration exhibited reduced dynamic efficiency due to adverse righting moment characteristics.

Overall, the findings confirm that mechanically feasible variable-geometry integration significantly enhances the adaptability and performance of two-body WECs. The proposed design offers a scalable and robust solution for improving wave energy conversion efficiency under realistic, variable sea-state conditions, supporting the advancement of practical and deployable wave energy technologies.

Finite Element Analysis and Multi-objective Optimization of the Spiral Sorting Device for Coal Mine Roadway Concrete Pavers

Lian Feng Ma — 2026-03-28

Aims: This study aims to conduct a comprehensive static analysis and lightweight multi-objective optimization of the spiral sorting device (auger) used in coal mine roadway concrete pavers. The primary objective is to fundamentally enhance the economic efficiency, structural reliability, and operational stability of the equipment under the harsh, confined, and demanding underground environments typical of modern coal extraction facilities.

Study Design: A rigorous numerical computational design combining advanced Finite Element Analysis (FEA) and statistical Response Surface Methodology (RSM) was deployed to systematically evaluate and optimize the mechanical structure.

Methodology: Initially, a rigorous mesh independence verification was discussed to ensure the absolute accuracy and computational efficiency of the numerical solutions. Subsequently, a detailed static analysis was performed by fixing both ends of the spiral shaft to simulate bearing constraints, applying a substantial surface load of 15000 N on the active faces of the spiral blades to simulate concrete resistance, and subjecting the spiral shaft to a driving torque of 573 N·m. Building upon the baseline static analysis results, a central composite design (CCD) was employed to construct a accurate mathematical response surface model. The spiral shaft diameter and blade thickness were selected as independent design variables, while the total structural mass, maximum total deformation, and maximum equivalent stress were established as the targeted objective functions. Finally, a Multi-Objective Genetic Algorithm (MOGA) was utilized to navigate the complex design space for global optimal searching based on Pareto efficiency.

Results: The initial comprehensive static analysis indicated that the maximum equivalent stress of the spiral sorting device was intrinsically located at the root of the blade, peaking at 126.46 MPa. Concurrently, the maximum deformation was recorded at 1.2891 mm at the outermost blade tip. Both baseline values fully met the rigorous safety design requirements. Detailed sensitivity analysis subsequently revealed that the spiral shaft diameter possessed the most significant dominant impact on both total mass and structural deformation, whereas the blade thickness exerted a more pronounced, localized influence on the stress distribution at the blade roots. Through extensive MOGA optimization iterations, the optimal geometric parameters were mathematically determined and engineering-rounded to a shaft diameter of 44 mm and a blade thickness of 4 mm. Consequently, the mass of the newly optimized device was remarkably reduced from an initial 28.411 kg down to 23.056 kg. Simultaneously, the maximum stress increased to 196.56 MPa and the maximum deformation shifted to 2.4121 mm, both of which dynamically remain strictly and safely within the allowable physical limits of the selected material.

Conclusion: The optimized design strategy successfully and significantly reduced the unnecessary dead mass of the spiral sorting device, achieving the coveted lightweight construction without compromising the essential structural strength and operational stiffness. This in-depth research provides a solid theoretical foundation, robust numerical validation, and a practical engineering reference for the future development, upgrading, and manufacturing of intelligent paving equipment operating under severely constrained underground conditions.

SCSAF-YOLO: An Enhanced YOLOv5-Based Object Detection Method for Unordered Industrial Workpieces

Xiaokang Wang — 2026-03-31

To address the issues of degraded detection accuracy and high false-positive rates caused by densely distributed workpieces and complex background interference in industrial sorting scenarios, this paper proposes an improved object detection algorithm based on YOLOv5l, termed SCSAF-YOLO. A spatial-channel synergistic attention (SCSA) mechanism is introduced to jointly model channel dependencies and spatial localization cues, thereby enhancing feature representation under occlusion and dense object distributions. To alleviate sample imbalance and improve bounding box regression accuracy, a Focal and Efficient Intersection over Union (F-EIOU) loss is employed to replace the conventional CIOU loss. Furthermore, depthwise separable convolutions (DWConv) are partially integrated to reduce computational complexity and model parameters while preserving detection performance. Extensive experiments on a self-built industrial sorting dataset featuring multi-scene occlusion and dense object layouts demonstrate that the proposed method achieves 97.6% mAP50 and 69.2% mAP50–95, outperforming the baseline by 1.4% and 2.4%, respectively, and surpassing mainstream YOLOv8 and YOLOv10 models. Experiments on the VOC2007 dataset further verify the generalization ability, with improvements of 7.8% and 5.7% in mAP50 and mAP50–95, respectively. Ablation studies confirm the synergistic effectiveness of the proposed components, indicating the potential of the method for industrial visual sorting applications.

Evaluation of Cooling Load of a Building Envelope in Owerri, Nigeria to Support the Optimized Design of a Suitable Sub-Wet-Bulb Evaporative Cooling System

O. O. Mong — 2026-03-31

The work focuses on designing a comfort-cooling evaporative system for a pilot building in Owerri, using data derived from the building’s thermal conditions. The initial step involved estimating the building cooling load by identifying key design parameters, namely ambient climatic data for the location and the target indoor comfort parameters that the proposed system must deliver. In this case, the primary inlet air (dry-bulb) was assumed to be 36 °C with 40-60% relative humidity, reflecting the local climate, while the target indoor conditions were set to a dry-bulb of 24.5-27 °C and 50-60% RH, appropriate for tropical air-conditioning. For the office space located at latitude 5°29′ N, longitude 7°0′ E, the cooling load was calculated to be 1 kW (with a 10% safety factor), equivalent to approximately 0.3 tons of refrigeration. Using this load, the system components were sized from first principles and design guidelines, arriving at a heat-exchanger area of 0.7 m², fan and pump power in the range of 300-370 W, working air ratio of 0.3, a 10-litre water reservoir and locally sourced poorly weaved fibrous fabric. The deployment of these design parameters enabled the production of an innovative, energy-efficient, eco-friendly sub-wet-bulb evaporative cooling solution for buildings in Owerri, Nigeria.

Evaluating Alternative Sources of Powering Thermomat for Gold Extraction in Ghana: A Multi-criteria Decision-making Perspective

John Awuah Addor — 2026-03-31

Gold has a substantial economic worth; it is an indispensable economic commodity for investment, sensitive electronic design and applications. Nonetheless, both the adverse environmental impacts and high cost of operations emanating from the complex processes engulfing gold extraction inevitably endorses the need to adopt sustainable energy inputs. This study therefore evaluates alternative sources of power for thermomat operations in gold extraction in Ghana. The main purpose of the study was to evaluate the performance of diesel, LPG and electricity as existing sources of powering thermomat for gold extraction in Ghana. The main method applied is the multi-criteria decision-making (MCDM) model. Two new recalling techniques were introduced to enhance symmetrical and fair distribution of scores across datasets. Aggregate weighted normalized scores (AWNS) were computed using quantitative data collected via questionnaire administration and desk search methods. Both quantitative and historical designs were used. A sample size of 563 comprising 60 from the top-management stratum, 3 from stakeholder stratum was obtained through convenient sampling; and 500 from the inhabitant stratum through simple random sampling. It was discovered that LPG presents the best power alternative with the highest AWNS of 1 in respect of economic feasibility, while electricity ranks the best power source with highest AWNS of 0.82 and 1 subject to environmental impacts and regulatory and policy implications respectively. LPG ranks the best power source with highest average AWNS of 0.8241 for all consolidated criteria. This research therefore, has essential implications for sustainability in mining operations and environment.