Claim Missing Document
Check
Articles

Found 2 Documents
Search

Machine-Learning-Based Vibration Classification of Inter-Module Connector Stiffness Loss in Modular Flood-Response Structures: A Simulation-Based Proof of Concept Sely Novita Sari; Fitri Nugraheni; Bagus Gilang Pratama; Ignatius Adi Prabowo
International Journal of Hydrological and Environmental for Sustainability Vol. 5 No. 3 (2026): International Journal of Hydrological and Environmental for Sustainability
Publisher : CV FOUNDAE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/ijhes.v5i3.1456

Abstract

Ensuring the safety of modular facilities used for flood response and post-disaster sheltering requires reliable assessment of inter-module connections that may deteriorate under hydrodynamic loading, debris impact, repeated wetting, and corrosion. This study presents a simulation-based proof of concept for classifying connector residual stiffness from vibration response using machine learning. Flood-load analysis quantified hydrostatic, hydrodynamic, and debris-impact forces under five severity scenarios, which were hypothetically associated with seven prescribed connector-stiffness levels ranging from 100% to 5%. Only the stiffness-to-vibration relationship was physically simulated; the flood-exposure-to-stiffness relationship was assumed rather than experimentally validated. Finite element modal analysis in OpenSeesPy provided the first four natural frequencies and mode shapes, from which sixteen diagnostic features were derived. Gaussian perturbations generated 350 synthetic realizations from the seven deterministic stiffness states. To minimize data leakage, classifiers were evaluated using block-grouped cross-validation and compared with majority-class and second-mode-frequency baselines. Random Forest achieved the best multiclass performance, with a macro-F1 of 0.62 and balanced accuracy of 0.63, although early-stage deterioration classes remained difficult to distinguish. When reformulated as a binary severe/non-severe screening task, the model achieved 0.94 balanced accuracy with a 0.10 false-safe rate. These results demonstrate within-configuration separability under synthetic noise rather than field generalization. The proposed framework may support rapid condition screening of modular connections, but experimental validation of the degradation mapping, structural model, and sensing strategy is required before field implementation.
Ceramic Floor Installation Waste and Selected Greenhouse-Gas Emissions: A Partial Installation-Related Life Cycle Inventory with Screening-Level GHG Characterisation Fitri Nugraheni; Sely Novita Sari; Deprizon Syamsunur
International Journal of Hydrological and Environmental for Sustainability Vol. 5 No. 3 (2026): International Journal of Hydrological and Environmental for Sustainability
Publisher : CV FOUNDAE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/ijhes.v5i3.1457

Abstract

The installation stage (module A5) of building-material life cycles is poorly represented in life cycle assessment (LCA) databases, particularly for developing-country practice. This study reports a partial, installation-related life cycle inventory (LCI) with screening-level greenhouse-gas (GHG) characterization not a full cradle-to-grave LCA for ceramic floor tiling, and documents the installation waste generated under one observed layout. Following the four-phase procedure of ISO 14040/14044 and the modular framework of EN 15804, a functional unit of 1 m² of installed floor was defined. The study quantifies only selected foreground flows: tile delivery transport (A4), cutting energy and offcut generation as selected A5 activities, and offcut-transport (C2); upstream manufacturing (A1–A3), most other A5 inputs (adhesive, mortar, grout, water, packaging, cleaning, equipment), end-of-life treatment (C3–C4), and the use stage were not quantified. Detailed measurements were obtained from one regular, unobstructed 48 m² reference room installed with a center-referenced, straight-lay pattern within a hospital project in Central Java. A waste factor of 2.33% (unrecovered offcut area over installed area) was observed in this room; total offcut generation was 3.33% and internal reuse recovered a further 1.00%. No alternative layout, corner-referenced start points, or optimization scenario was evaluated, so the value is reported as a case-specific observation rather than evidence that the layout prevented waste. Within the selected and counted flows, and excluding A1–A3, delivery transport (A4) contributed approximately 98% of the calculated GHG under a loaded one-way assumption; including an allocated empty return raised the counted total by about 98% and the A4 share to roughly 99%. A sensitivity analysis across freight and grid emission factors, return-trip treatment, transport distance, load factor, waste baseline (5/8/10%), and reuse substitution (0/50/100%) confirmed that conclusions are contingent on the narrow boundary and adopted factors. The study's contribution is a documented primary-data case inventory for selected ceramic-tile installation activities in Indonesia, not a validated waste-prevention model.