
Purpose The study aims to develop an intelligent prediction framework for dual-crack coalescence behavior and enhance the prediction accuracy and generalization performance of crack state judgment under multiple crack morphologies. Design/methodology/approach Four typical machine learning classifiers including LR, KNN, SVM and KELM are comprehensively compared on datasets of linear, elliptical and circular dual cracks. The Kernel Extreme Learning Machine (KELM) with the best overall performance is selected as the base model. A Reinforced Multi-strategy Parrot Optimization (RMPO) algorithm is employed to globally optimize KELM's hyperparameters, taking regularization coefficient C and RBF kernel parameter as optimization variables. The negative average validation-set accuracy from inner-fold cross-validation is adopted as the fitness function for adaptive searching within a nested stratified cross-validation workflow. Findings KELM outperforms other machine learning models in predicting three types of dual-crack coalescence. After hyperparameter tuning by RMPO, the hybrid RMPO-KELM model achieves prediction accuracies of 0.973, 0.911 and 0.824 for linear, elliptical and circular dual cracks respectively. Compared to grid search (GS) and the Parrot Optimization Algorithm (PO), the optimized model achieves a more accurate nonlinear fit between crack geometric inputs and coalescence labels, and maintains reliable prediction accuracy on independent test subsets. Research limitations/implications This study only considers dual cracks in homogeneous plates under predefined loading conditions. The dataset is derived from numerical simulations, and further physical tests are required to validate the model. Future work can extend the model to heterogeneous materials, multiple cracks and complex load cases. The feature selection strategy may be further refined for broader engineering scenarios. Practical implications This proposed RMPO–KELM model enables fast identification of dual-crack coalescence states in homogeneous plates, avoiding heavy finite-element iterative computation. It offers an efficient auxiliary tool for structural safety assessment. The feature screening scheme also provides a reference for selecting dimensionless crack parameters. Engineers can adopt this framework for preliminary crack risk evaluation in similar plate structures. Social implications Accurate and rapid prediction of crack coalescence helps prevent sudden structural failures in infrastructure, reducing safety hazards and casualties. Reliable structural risk assessment extends service life of engineering components, cuts maintenance costs and lowers resource consumption. This predictive framework supports safer civil and mechanical infrastructure, benefiting public safety and sustainable asset management. Originality/value An RMPO–KELM hybrid intelligent prediction model is proposed for multi-morphology dual-crack coalescence prediction. The RMPO algorithm realizes efficient global searching of KELM hyperparameters, which significantly improves prediction precision and generalization capacity. This work supplies a data-driven solution for structural safety assessment involving crack propagation and coalescence.
Purpose This research elucidates two assumptions regarding the initiation mechanism and practical detectability of micro-cracks in welded joints made of S235JR steel, as well as their often-neglected influence on structural integrity. Design/methodology/approach Research investigates the initiation, detection and influence on structural integrity of small defects, specifically (in most cases neglected) micro-cracks in the weld root, made under controlled laboratory conditions. Consequently, this research investigates two assumptions (through two welding procedures) that can lead to initiation of micro-cracks in welded joint root, while the influence of discovered micro-cracks discovered by microstructural analysis were examined via failure assessment diagram (FAD). Findings Detected micro-cracks are sharp with potential towards further propagation. Examined micro-crack with depth of 0.3 mm lies deep within the safe region of the FAD; its presence and its growth could compromise structural integrity. Research limitations/implications Future research will be focused on more comprehensive investigation on micro-cracks initiation in welded joint with the practical impact on structural integrity assessment of welded structures by using analytical and numerical methods. In addition, the study emphasizes the practical limitations of conventional non-destructive testing (NDT) methods in detecting micro-cracks and emphasizes the need for development and use of more advanced methods. Practical implications This study's findings suggest that the focus regarding structural integrity analysis should shift to more detail characterizing and understanding the mechanisms of micro-crack initiation, detection and propagation, in addition to detecting larger defects. Given that conventional NDT methodologies failed to identify these sub-millimeter defects, the presented approach indicates their importance, especially if located in critical zones in welded joint such as the weld root. Social implications Indirectly, the findings of this study emphasize the necessity of early micro-crack detection, which can directly contribute to the prevention of catastrophic failures along with associated economic consequences. Originality/value The originality of this research lies in the dual experimental and analytical characterization (via FAD) of micro-cracks in structural steel welded joints. These defects can significantly impair overall structural integrity through inevitable crack growth under tensile loading.
Purpose This study investigates the failure mechanism of a cracked piping elbow in a crude-oil transport system after approximately 20 years of service, with the aim of identifying the dominant degradation mechanisms and assessing structural integrity using numerical and risk-based approaches. Design/methodology/approach The study combines field inspection, non-destructive testing, wall-thickness measurements, fracture-mechanics concepts, finite element method (FEM)/extended finite element method (XFEM) numerical simulations and American Petroleum Institute: API 581-based risk-based inspection (RBI) analysis. Findings The results showed that the failure was caused by the combined action of erosion–corrosion, naphthenic acid corrosion, localized corrosion and pressure transients. Numerical simulations identified the elbow–pipe transition as the critical stress region, consistent with the observed crack location. Research limitations/implications The analysis was based on a real industrial case study and limited by the absence of experimentally determined fracture toughness data. Nevertheless, the integrated methodology provides useful insight into localized degradation and failure development in aging pipeline systems. Practical implications The study demonstrates the importance of combining inspection data, numerical analysis and RBI methodologies in the integrity assessment of geometrically sensitive pipeline components. The results support complete elbow replacement as the most reliable remediation strategy. Social implications The study contributes to improved operational safety and reliability of aging oil-transport infrastructure by supporting earlier identification of locally critical damage mechanisms that may lead to leakage and environmental incidents. Originality/value The study presents an integrated analysis of a real pipeline elbow failure combining field observations, FEM/XFEM simulations, fracture-mechanics concepts and RBI methodology. The study highlights how multiple moderate degradation mechanisms can interact to produce locally critical conditions that may be underestimated by global risk assessments.
Purpose This research aims to evaluate how manufacturing processes influence stress-corrosion cracking in two supermartensitic stainless steels (SMSSs) classified as UNS S41426. The samples were manufactured by forging and hot rolling process. Design/methodology/approach The microstructures of both materials were investigated by light optical microscopy, scanning electron microscopy, electron backscattered scanning diffraction, X-ray diffraction and magnetic measurements. Stress corrosion cracking was investigated using slow strain rate testing (SSRT). In the SSRT tests, two solutions were employed, both containing 200 g/L of NaCl at ppH2S 0.5 psi and a total pressure of 14.5 psi, at room temperature. The solutions were distinguished by the carbonate concentration and the pH level, 5.0 and 5.5. Findings The grain size of the forged sample is coarser than that of the hot rolled (HR). The microstructure of the 1'forged had more reverse austenite than the hot-rolled one, and this austenite forms fresh martensite during deformations of SSRT. In solution at pH 5.0, the more aggressive one, both materials exhibit brittle behavior with quasi-cleavage features and intergranular cracks near the exposed surface, and small dimples in the central part of the specimen. However, for the solution at pH 5.5, the less aggressive one, the forged piece presents a similar fracture, while the HR piece shows a ductile fracture. Originality/value Such a comparison of the behavior of forged and HR SMSSs with respect to the susceptibility to sulfide stress corrosion cracking, supported by microstructural analysis, has never been published. The value of this study lies in the fact that not only the UNS designation number, but also the processing route, must be taken into account to select the material for harsh environmental conditions found in deep-water oil reservoirs.
Purpose This work provides a structural integrity assessment of a spent fuel casks using BS7910. The containment barrier of the casks is designed following ASME Section III. Accordingly, it is necessary to demonstrate the integrity of the materials all along the range of operation temperatures, based on the determination of the corresponding reference temperature for nil-ductile temperature. This approach may be very conservative for the case being analyzed, with a low Lowest Service Temperature, −40°C, established to obtain the Certificate of Compliance for a Type B(U) package. The present work provides an alternative analysis to evaluate and guarantee the structural integrity. Design/methodology/approach The analysis is based on the use of the BS7910 and a number of engineering conservative assumptions for the treatment of material properties, defect types and loading conditions. Findings The results show that the cask operation is safe in both Normal Operating Conditions (NOC) and Accidental Conditions (AC), also complying with minimum safety factors established by the nuclear industry for this kind of components and applications. Originality/value The work provides a sound original methodology for assessing the structural integrity of casks in cases where the direct application of ASME Code Section III is not capable of demonstrating the absence of non-ductile fracture.