Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.

المخرجات

Research outputs

Articles, reviews, conference papers and book chapters, indexed by DOI and linked to University researchers.

2 output Results for «diagnostic framework»

ArticleOpen access2026

Global thermodynamic consistency: A linear-algebraic diagnostic framework

Results in Engineering · vol. 32 · 112122-112122

Thermodynamic cycle models are routinely assembled from heterogeneous sources – steam-table lookups, manufacturer data sheets, handbook correlations, and hand-computed preliminary estimates – and an error introduced in any one source (a misread enthalpy, a sign error in a heat balance, a wrong coefficient-of-performance value) can propagate silently through every downstream calculation. Engineers currently guard against this by checking governing equations pairwise, but pairwise checking has a structural blind spot: a set of equations can pass every pairwise comparison and still be globally infeasible as a system. We develop a linear-algebraic diagnostic framework that closes this gap. The governing equations of a steady-state thermodynamic cycle – energy balances over turbines, compressors, boilers, condensers, and expansion devices, together with isentropic-process relations and the coefficient-of-performance definition – form a linear system A x = b whose state vector x collects enthalpies, heat transfer rates, and work quantities at each process node. We show that global inconsistency of this system is equivalent to infeasibility of A x = b , and that infeasibility is always witnessed by a vector in the left nullspace of A that is not orthogonal to b – an algebraically certifiable condition we call a nullspace inconsistency certificate , computable from a single thin SVD and fundamentally inaccessible to pairwise checking. Building on this certificate, we prove that pairwise consistency checks are provably insufficient to detect global thermodynamic inconsistency; we establish existence and uniqueness of a minimum-norm repair vector that returns the right-hand-side data to the nearest feasible point on the constraint manifold; we derive equation-localization weights that rank which governing equation is the primary source of a fault; and we construct a differentiable repair operator whose fixed points correspond to globally self-consistent cycle models. The complete detection-localization-repair pipeline runs in O ( kn 2 ) time via a thin SVD – negligible overhead for cycle models of practical size – and requires no information beyond the equations and data an engineer already has on hand. We demonstrate the framework on the Rankine steam-power cycle and the vapor-compression refrigeration cycle, where it correctly detects, localizes, and corrects hidden inconsistencies – including a 50 kJ kg − 1 enthalpy error in Rankine cycle steam tables and a simultaneous condenser-balance fault with an erroneous COP value in the refrigeration cycle – that pass all pairwise equation checks yet render the global model infeasible. We further discuss how the certificate behaves under measurement and property-estimation uncertainty, and compare the approach against residual-based checking, data-reconciliation, and optimization-based fault detection. The framework requires only the linear (or linearized) governing equations and standard property data already used in routine cycle calculations, making it directly deployable as an auditing layer in existing engineering workflows.

thermodynamic consistencylinear algebradiagnostic frameworkenergy balance
ArticleOpen access2025

HearteXplain: explainable prediction of acute heart failure and identification of hematologic biomarkers using EBMs and Morris sensitivity analysis

Scientific Reports · vol. 15 (1) · 39971-39971

Hematological biomarkers have emerged as powerful tools in diagnosing Acute Heart Failure (AHF). This study introduces a novel diagnostic framework that integrates Explainable Artificial Intelligence (XAI) with Morris Sensitivity Analysis (MSA) to enhance both the interpretability and performance of machine learning models in AHF detection. A dataset consisting of 425 AHF patients and 430 controls was analyzed using eight machine learning models, including XGBoost, Histogram-based Gradient Boosting (histGB), Explainable Boosting Machine (EBM), and Random Forest. Model performance was evaluated through metrics such as AUC, accuracy, precision, recall, and Brier score. Hyperparameters were optimized via Bayesian optimization. Feature importance was assessed using MSA to identify variables with the highest predictive influence. The histGB model achieved the highest performance with an AUC of 87.93%. Both MSA and EBM consistently identified PDW, RDW-CV, NEU, NEU/LY ratio, age, and WBC as top predictive features across multiple models. These hematological markers demonstrated strong potential for early diagnosis and risk stratification in AHF patients. This study presents a clinically relevant, interpretable, and cost-effective diagnostic strategy that combines XAI with MSA for AHF prediction. The framework enhances clinical trust and provides a pathway toward personalized treatment by identifying accessible hematological biomarkers. The integration of explainability into AI models improves their transparency and applicability in real-world clinical settings.

acute heart failurehematological biomarkersexplainable AIexplainable boosting machine