Engine Components Research Articles

Deep Rolling Techniques: A Comprehensive Review of Process Parameters and Impacts on the Material Properties of Commercial Steels

The proposed review demonstrates the effect of the surface modification process, specifically, deep rolling, on the material surface/near-surface properties of commercial steels. The present research examines the various process parameters involved in deep rolling and their effects on the material properties of AISI 1040 steel. Key parameters such as the rolling force, feed rate, number of passes, and roller geometry are analyzed in detail, considering their influence on residual stress distribution, surface hardness, and microstructural alterations. Additionally, the impact of deep rolling on the fatigue life, wear resistance, and corrosion behavior of AISI 1040 steel is discussed. Engineering components manufactured by AISI 1040 steel can perform better and last longer when deep rolling treatments are optimized with an understanding of how process variables and material responses interact. This review provides critical insights for researchers and practitioners interested in harnessing deep rolling techniques to enhance the mechanical strength and durability of steel components across diverse industrial settings. In summary, the valuable insights provided by this review pave the way for continued advancements in deep rolling techniques, ultimately contributing to the development of more durable, reliable, and high-performance steel components in diverse industrial applications. The establishment of generalized standardizations for the deep rolling process proves unfeasible because of the multitude of controlling parameters and their intricate interactions. Thus, specific optimization studies tailored to the material of interest are imperative for process standardization. The published literature on the characterization of surface and subsurface properties of deep-rolled AISI 1040 steel, as well as process parameter optimization, remains limited. Additionally, numerical, analytical, and statistical studies and the role of ANN are limited compared with experimental work on the deep rolling process.

Reliability, Availability, and Maintainability Assessment of a Mechatronic System Based on Timed Colored Petri Nets

The mechatronic industry is currently subject to huge changes challenging it to offer products matching individual customer requirements at competitive prices. The design of such products calls for sophisticated and complex components integration following different technologies. Since we are on the cusp of the Fourth Industrial Revolution, in which the world of mechatronic production, network connectivity, the Internet of Things, and cyber-physical systems are correlated, the complexity of these systems increases exponentially, and we are talking about advanced mechatronic systems. To assist these changes, various methods, sweeping all project phases, are used by business houses. Predictive dependability assessment in the earlier design stage is considered a powerful metric used to evaluate the performances of different kinds of mechatronic products before the production phase. Altogether, dependability analysis ties the design directly to the desired functionality, operability, and integrity of the system. This paper explores an approach to assessing the dependability attributes, reliability, availability, and maintainability (RAM), of repairable mechatronic systems based on timed colored Petri nets and a Monte Carlo simulation, integrating simultaneously diverse components technologies: mechanical, electronic, and software. The proposed approach is tested taking the case of a regenerative braking system. The methodology appears to be efficient for evaluating predictive RAM indicators (MTTFF, MTTR, MTBF…) for the whole system and for each individual component separately.

INTEGRATING MACHINE LEARNING AND BIG DATA ANALYTICS FOR REAL-TIME DISEASE DETECTION IN SMART HEALTHCARE SYSTEMS

The integration of machine learning (ML) and big data analytics within smart healthcare systems represents a transformative advancement in medical services, emphasizing efficiency, accuracy, and patient-centered care. This paper investigates the application of these advanced technologies in real-time disease detection, showcasing their potential to revolutionize healthcare delivery. Smart healthcare systems leverage a multitude of technological components, including Internet of Things (IoT) devices, sensors, and artificial intelligence (AI), to enable continuous monitoring and diagnostics. This real-time monitoring facilitates prompt interventions and treatment adjustments, which is particularly advantageous for managing chronic conditions and acute illnesses where timely responses are critical to improving patient outcomes. Despite the evident benefits, traditional healthcare infrastructures face significant challenges such as delays in diagnosis due to manual processes, inefficient data handling resulting in data silos, and limited interoperability between different healthcare providers, leading to worsened health outcomes and increased healthcare costs. The integration of ML and big data analytics offers promising solutions to these challenges. ML algorithms can process vast amounts of healthcare data to identify patterns and predict outcomes with high accuracy, such as recognizing early signs of diseases like cancer or diabetes from medical images or electronic health records (EHRs). Big data analytics complements ML by providing the necessary infrastructure to handle and process large volumes of health data, enabling the collection, storage, and analysis of structured data from EHRs, unstructured data from clinical notes, and real-time data from wearable devices. By integrating these technologies, healthcare providers can gain deeper insights into patient health trends and outcomes, leading to more informed decision-making and better patient management. This study employs a qualitative research design, focusing on five genuine case studies: the Mayo Clinic's predictive analytics for heart disease, Cleveland Clinic's use of ML for cancer diagnosis, Kaiser Permanente's diabetes management program, Johns Hopkins Hospital's sepsis detection system, and Mount Sinai Health System's genomic data analysis. Each case study is chosen for its relevance and comprehensive data, detailing the specific healthcare environment and context. This paper interprets these findings in the broader context of smart healthcare systems and existing literature, emphasizing the importance of these technologies in modernizing healthcare and addressing inefficiencies. The challenges encountered during integration, such as data privacy concerns and interoperability issues, are examined along with implemented solutions.

Journeys Through Genomics: Co-Producing Visual Resources to Communicate Patient Experiences

Journeys through Genomics is a series of illustrations co-produced with patients and families to communicate their experiences of seeking genomic explanations for a health condition and the wider impact on their lives. The resources are embedded within qualitative longitudinal research exploring patient’s experiences of genomic medicine. This research takes place as genomic medicine becomes an integral part of mainstream care within the UK healthcare system. The depiction of genomic medicine often focuses on its technological components and the speed by which genetic code can be analysed, but here, we present a dynamic and situated understanding of the challenges genomic testing presents for patients and families. We describe the process of working with research participants and an artist to co-produce visual resources that illustrate the complexity of participant’s journeys, situating genomic testing within the broader context of their lives. These resources are designed to help future patients, families, and healthcare professionals understand the process, opportunities, and challenges they may face.

AI-Based Detection of Surge and Rotating Stall in Axial Compressors via Dynamic Model Parameter Estimation

Compressors are an essential component of aircraft engines. Their design and operation must be extremely reliable as engine safety and performance depend greatly on these elements. Axial compressors exhibit instabilities, such as surge or rotating stall, in a region close to the peak of their performance curves. These fluid dynamic instabilities can cause drops in efficiency, stress on the blades, fatigue, and even failures. Compressors are handled therefore by operating with a safety margin far from the surge line. Moreover, models able to predict onset instabilities and to reproduce them are of great interest. A dynamic system able to describe successfully both surge and rotating stall is the model presented by Moore and Greitzer That model has also been used for developing control laws of the compressor dynamics. The present work aims at developing an artificial neural network (ANN) approach able to predict either the permanence of the system in stable working condition or the onset instabilities from a time sequence of the compressor dynamics. Different solutions were tried to find the most suitable model for identifying the system, as well as the effects of the duration of the time sequence on the accuracy of the predicted compressor working conditions. The network was further tried for sequences with different initial values in order to perform a system analysis that included multiple variations from the initial database. The results show how it is possible to identify with high accuracy both rotating stall and surge with the ANN approach. Moreover, the presence of an underlying fluid dynamic model shares some similarities with physically informed AI procedures.

Preparation of Eu ions doped Sr5(PO4)3F transparent glass ceramics and their luminescence properties

The lack of red light components in solid-state lighting technology urgently requires the development of new efficient red-emitting bulk phosphors. Herein, we successfully prepared a kind of red-emitting glass ceramics (GCs) (λex = 392 nm, λem = 613 nm) containing Eu-doped strontium fluorophosphates (Sr5(PO4)3F:Eu) nanocrystals via a melt-quenching method in SrF2–K2CO3–P2O5–H3BO3 glass. The heat treatment temperature was found to significantly affect the grain size of the Sr5(PO4)3F:Eu nanocrystals as well as the transmittance of the prepared GCs. After heat treatment at 600 °C for 2 h, the Sr5(PO4)3F:Eu nanocrystals with grain size of about 18 nm were precipitated inside the GCs (GC600), which exhibited a high transmittance of 58–70 % in the range of 500–800 nm, with a stronger luminescence intensity than that of PG. Under excitation of 392 and 464 nm wavelengths, the CIE 1931 color coordinates of GC600 were around (0.626, 0.373) and (0.638, 0.362), respectively, both falling in red region. The present Sr5(PO4)3F:Eu GCs are promising as red phosphors for UV-pumped white-light LEDs.

Numerical Simulation of Workflow for Evaluating Flame Tube Thermocyclic Durability

ABSTRACT This paper explores strategies for extending the operational lifespan of flame tubes in turbofan engines – a critical component for maintaining engine efficiency and reliability, in line with global trends aimed at maximizing the use of laid reserves of aircraft engine performance. Utilizing a combination of advanced computational simulations and empirical research, the study meticulously analyzes the internal processes within the flame tube of the AL-31F turbofan engine. A detailed geometric model and finite element grid were created and adapted to simulate various operating conditions and assess their impact on the flame tube’s performance. Special attention is given to understanding the thermal and mechanical stresses that influence its durability and serviceability. The results, compared against experimental data, validate the simulations and are crucial for identifying critical sections prone to damage, thereby facilitating enhanced decision-making regarding maintenance schedules and overhaul practices. This approach not only aims to minimize downtime and reduce maintenance costs but also extends the service intervals for critical engine components, thereby improving thermocyclic durability based on the damage mechanisms identified.

Grain Quality Evaluation of Several Upland Rice Varieties in Indonesia

Abstract High-yielding rice varieties that are adaptive to dry land conditions are the main technological component in efforts to increase rice production also known as upland rice. This study aimed to determine the physical quality, milling quality, physicochemical characteristics, and sensory test of six upland rice new superior varieties namely Inpago 8, Inpago 10, Inpago 12, Inpago Unsoed, Rindang 1 and Rindang 2. The quality analysis was carried out at Rice Quality Laboratory, Indonesian Center for Rice Research (ICRR) in Sukamandi, West Java, Indonesia. Furthermore, rice quality data is compared with the Indonesian National Standard (INS) for paddy No. 0224-1987/SPI-TAN / 01/01/1993 and with INS of rice No 6128:2020. The result showed that upland rice varieties have the criteria of the third class of INS paddy. Out of six varieties, four varieties were categorized as long rice and the rest were medium rice (Inpago 8 and Inpago Unsoed). All varieties were classified as medium shape. According to milling quality, Inpago 12 followed by Inpago 8 has the best yield of brown rice. Meanwhile, the best yield of milled rice was Inpago 12 followed by Inpago 10. All varieties met the percentage of head rice (maximum 75%) and broken rice (maximum 22%) for the second medium class. The Inpago 8, Inpago 10, Inpago 12, and Inpago Unsoed varieties belong to the low to medium amylose group, having a medium gel consistency with a separated and fluffy cooked rice texture character. According to the sensory test findings for cooked rice, there were no differences among any of the kinds in terms of flavor, color, shine, taste and overall evaluation. Based on physical, milling quality and physicochemical characteristics, Inpago 12 is the best variety of all the upland varieties observed.

Evaluation of pre-service Science and Math teachers’ online teaching experiences within the TPACK framework

The purpose of this study is to identify the factors that shape pre-service teachers' (PSTs) online teaching practices within the technological pedagogical content knowledge (TPACK) framework. Ten science PSTs and nine mathematics PSTs who experienced the practical part face-to-face and the theoretical part online of the Teaching Practice 2 course participated in this study based on a multiple case study design. The researchers collected data through online lesson videos and the TPACK in Online Teaching Survey. Descriptive statistics were used for the survey analysis, while the document analysis technique was through TPACK in Online Teaching Checklist for online lesson videos. The results show that PSTs have some problems, especially in the technological and pedagogical knowledge components of TPACK. Both groups do not have adequate knowledge of the technological tools of assessment, because they give it the least importance. They generally use standard technologies such as presentations or office programs. Their use of the same technologies to identify and teach the subject indicates their limited conceptualizations of technological pedagogical knowledge (TPK) and technological content knowledge (TCK). PSTs need improvement in promoting teacher-student interaction through interactive learning and assessment tools. Some recommendations for teacher education programs are offered.

Perbandingan Keutuhan Permukaan Bahan Inkonel 718 dalam Pemesinan Kriogenik dan Kering

Inconel 718 is a nickel-based alloy that has been developed with superior mechanical strength, creep resistance, and corrosion, as well as erosion resistance at temperatures above 649 ˚C. It is suitable to be used for aircraft engine components such as turbine discs. However, it also has low heat conductivity and the presence of hard carbide particles in its alloy worsens the machining conditions with high cutting temperature, and high shear force and promotes work hardening. Thus, this study aims to evaluate the surface integrity of Inconel 718 in terms of surface roughness, plastic deformation, and micro-hardness alterations after the turning process. Cryogenic CO2 cooling was supplied along the cutting process to reduce cutting temperatures and the machining performances were compared with dry machining. The experimental works show that the dry machining resulted in lower surface roughness by up to 42.15% as compared to cryogenic. However, the depth of plastic deformation under dry machining was much more severe than in cryogenic machining driven by higher cutting temperatures and pressure from the worn tool. The depth of plastic deformation became more distinct as the cutting speed increased. While the microhardness alteration of the machined surface was higher under cryogenic machining due to extensive cooling capacity by the CO2 flow. Thus, this study reveals that cryogenic cooling during metal cutting can produce products that have better wear resistance as well as higher surface hardness.

Identifikasi Kenaikan Suhu Minyak Lumas Pada Motor Induk di MV. Manalagi Dasa

Lubrication is one aspect that must be paid attention to, remembering that if there is a delay in lubrication or imperfect lubrication, it will result in damage to the parts that rub together. Low lubricating oil pressure is one of the factors causing imperfect lubrication in the engine. The purpose of lubrication for the performance of the main engine is to reduce friction between other components of the main engine. This research was carried out at MV. Manalagi Dasa, the method used in this research was the Fishbone Diagram. The problem formulation of this research is what causes an increase in the temperature of the lubricating oil on the main motor and what is the impact of increasing the temperature of the lubricating oil on the main motor. Based on research that has been carried out, there are several factors that cause less than optimal lubrication of the oil cooler on the main engine, namely engine factors including damage to gaskets, human factors, namely the lack of understanding of the driver about the lo cooler, operational and maintenance method factors, namely incompatibility in implementing the PMS (Plan Maintenance System) as well as environmental factors, namely dirty sea chest filters. Efforts made include repairing or replacing gaskets on the lo cooler plate, the importance of the machinist's understanding of the lo cooler, implementing PMS (Plan Maintenance System), and cleaning the sea chest filter.

Strategy adaptive system to learning processes for emerging serious games using a fuzzy classifier system

An emerging serious game (ESG) is a game that unfolds autonomously without explicit laws, adapting to the player, where the player learns while playing. An ESG engine must enable the emergence in the game, in order to allow its adaptation to the specific environment where it is being used. In previous articles, different components of an ESG engine have been proposed. This paper proposes a strategy adaptive system (SAS) for ESG, which allows the emergence of strategies in a videogame. Particularly, SAS manages the emergence of new procedures or methods (tactics), as well as actions (logistics), among other things, in the ESG, to adapt it to the environment. This component is based on a Fuzzy Classifier System that generates new rules, tactics, etc. in the game to follow the desired behavior. In this article, SAS is applied in a smart classroom (SaCI, for its acronym in Spanish), in such a way that allows the adaptation of an ESG to the students in SaCI. Especially, it is used during their teaching-learning processes. Additionally, this paper analyzes the performance of SAS in SaCI, with very encouraging results, since the quality of the strategies proposed by SAS (defined by rules that define the logic and tactics of the game) is improved in all case studies. This improvement is confirmed because the average use of the rules generated by our adaptive system is greater than 3.6, when the initial rules are used on average less than once.

Corrosion characterization of engine connecting rods using fringe projection profilometry and unsupervised machine learning

The consequences associated with corrosion, a global industrial peril, cost an estimated $ 2.5 trillion annually to inspect, rectify, and prevent. In addition to significant economic losses, corrosion-induced failure of critical components in transport systems, like automobiles, may also lead to loss of human life. Hence, it is essential to eradicate corrosion in its early stages. The most vital automobile component is its engine, whose failure can cause fatal accidents. Regular quality inspection and maintenance by skilled personnel is essential to prevent this. Automating this task will address this domain’s personnel shortage while mitigating the risk of human error. To enable the performance of this task without the need for human intervention, we determine the morphological parameters affected by corrosion in automotive engine components, namely connecting rods, using fringe projection profilometry, a high-speed 3D profiling technique capable of achieving sub-millimeter accuracy. We then perform classification using k-means clustering into low, medium, and high corrosion bands, based on the parameters obtained from 3D imaging. The model was able to achieve a high accuracy of 88.57%. The accuracy was determined by considering the visual classification performed by a Material Science Expert as the ground truth.

A multilevel graph approach for IoT-based complex scenario management through situation awareness and semantic approaches

AbstractModern reality and the environments in which we live are characterized by technology components geared toward automatic management through pervasive services. Thanks to the advent of the Internet of Things, such environments can provide information such as pollution levels, public transport conditions, efficiency of energy distribution networks, and identification of suspicious activities by generating complex scenarios. The profitable management of such scenarios can be performed through context modeling and methodologies that can extract and understand environmental information by preventing certain events through artificial intelligence techniques by increasing Situation Awareness. This paper focuses on developing a methodology with predictive capabilities and context adaptability for managing complex scenarios. The use of semantic and graph-based approaches, unlike many approaches used, leads to better integration of knowledge, resulting in improved system performance. In addition, such approaches allow understanding of what is happening in the system at a given time, enabling manipulation and integration of semantic information. Graph-based approaches chosen for this purpose are Ontologies, Context Dimension Trees, and Bayesian Networks, which are able to support the end-user or expert user in handling complex scenarios. The proposed methodology has been validated and applied to real complex scenarios based on the IoT paradigm. The proposed approach validation was conducted using open data from the city of London; a practical scenario case study was conducted in the field of automated management of a Smart Home. In both cases, the system achieved promising results.

Optimal design of structural engineering components using artificial neural network-assisted crayfish algorithm

Abstract Optimization techniques play a pivotal role in enhancing the performance of engineering components across various real-world applications. Traditional optimization methods are often augmented with exploitation-boosting techniques due to their inherent limitations. Recently, nature-inspired algorithms, known as metaheuristics (MHs), have emerged as efficient tools for solving complex optimization problems. However, these algorithms face challenges such as imbalance between exploration and exploitation phases, slow convergence, and local optima. Modifications incorporating oppositional techniques, hybridization, chaotic maps, and levy flights have been introduced to address these issues. This article explores the application of the recently developed crayfish optimization algorithm (COA), assisted by artificial neural networks (ANN), for engineering design optimization. The COA, inspired by crayfish foraging and migration behaviors, incorporates temperature-dependent strategies to balance exploration and exploitation phases. Additionally, ANN augmentation enhances the algorithm’s performance and accuracy. The COA method optimizes various engineering components, including cantilever beams, hydrostatic thrust bearings, three-bar trusses, diaphragm springs, and vehicle suspension systems. Results demonstrate the effectiveness of the COA in achieving superior optimization solutions compared to other algorithms, emphasizing its potential for diverse engineering applications.

Investigation of pad radius effects on multiaxial fretting fatigue behavior of al2024 alloy

Fretting fatigue, a critical phenomenon prevalent in engineering applications, occurs at the interface of contacting surfaces under cyclic loading, presenting significant challenges. The advent of Finite Element Analysis (FEA) has transformed the investigation of fretting fatigue by offering detailed insights into stress distributions and fatigue damage mechanisms. This study delves into the impact of pad radius on the fretting fatigue behavior of Al2024 alloy using FEA, with a focus on hot spot analysis and the Smith-Watson-Topper (SWT) criterion. The analysis aims to validate numerical results against analytical findings and explore the role of pad radius in determining contact behavior, fatigue life, and hot spot locations. By incorporating "fe-safe" software, computations are streamlined, facilitating efficient comparison of different fatigue initiation criteria. The results demonstrate that variations in pad radius significantly influence fretting fatigue behavior. Larger pad radii tend to distribute stresses more uniformly across the contact interface, resulting in reduced fatigue damage and longer fatigue life compared to smaller pad radii. Hot spot analysis reveals that smaller pad radii concentrate stresses at specific regions, accelerating fatigue damage initiation. The findings contribute to a deeper understanding of fretting fatigue mechanisms, shedding light on the importance of pad radius in designing more durable engineering components. Through professional scientific methodology, this study provides valuable insights into optimizing pad design to mitigate fretting fatigue and enhance the reliability of mechanical systems.

Predictive control method for mode transition process of multi-mode turbine engine based on onboard adaptive composite model

In order to achieve precise control of thrust and flow during the mode transition(MT) process of multi-mode turbine engine(MMTE) within the switching envelope and under the condition of engine performance degradation, research on multi-mode model predictive control method is conducted. A mode transition trajectory optimization method based on SQP is explored, and a small range of adjustable parameters that ensure the continuous thrust and flow is obtained. Based on this, a multi-mode onboard modeling approach based on the directional adjustment law scheduling of the variable geometry adjustment mechanism is proposed. Furthermore, an investigation into a predictive control method for MT process based on onboard adaptive composite model is conducted. The simulation results demonstrate that the proposed method exhibits a maximum thrust fluctuation of less than 0.66 % during MT process, under both normal and degraded engine component performance conditions, which is significantly superior to the conventional PID control of 2.8 %. Compared to the average single step calculation time of 7.24 ms using the SQP optimization method, the proposed approach only requires 0.204 ms. The methodology presented takes into consideration of control accuracy and computing efficiency, thereby offering promising prospects for engineering applications in MMTE MT control system design.

Transportation of Objects on an Inclined Plane Oscillating in the Longitudinal Direction Applying Dynamic Dry Friction Manipulations

A transportation system requires an asymmetry to achieve objects’ motion on an oscillating surface. Transportation methods based on vibrational techniques usually employ different types of asymmetries, such as temporal (time) asymmetry, kinematic asymmetry, wave asymmetry or power asymmetry. However, transporting an object on an inclined angle requires a relatively high net frictional force over each period of vibrational cycles due to the gravitational potential energy exerted on the object. This paper investigates the transportation of an object upward on an inclined plane that harmonically oscillates in its longitudinal direction. The novelty of this research is attributed to the upward motion of the object on the inclined plane, which is achieved by creating an additional asymmetry of the system through dry friction dynamic manipulations. For this reason, periodic dynamic dry friction manipulations have been employed to create the asymmetry of frictional conditions, resulting in a net frictional force that outweighs the gravitational force. A mathematical model has been developed using the Lagrange method, which describes the moving object’s motion. Moreover, the theoretical findings and results confirmed that the object’s velocity and direction can be controlled by dynamic dry friction manipulations. To demonstrate the technical feasibility of the proposed method, an experimental investigation was carried out where the results demonstrated that the control parameters significantly influence the characteristics of the directional motion of the moving object. This transportation method is beneficial for various modern industries engaged in transportation and manipulation tasks with objects spanning a broad range of sizes, including those operating at small scales for applications in lab-on-a-chip technology, micro-assembly lines, micro-feeder systems and other delicate component manipulation systems. The presented research advances the classical theories of vibrational transportation on inclined surfaces.

High Temperature Oxidation Behavior of Additive Manufactured Ti6Al4V Alloy with the Addition of Yttrium Oxide Nanoparticles.

Titanium alloys face challenges of high temperature oxidation during the service period when used as aircraft engine components. In this paper, the effect of Y2O3 addition on the oxidation behavior and the microstructural change of the Ti6Al4V alloy fabricated by selective laser melting (SLM) was comprehensively studied. The results show that the surface of the Ti6Al4V alloy is a dense oxide layer composed of TiO2 and Al2O3 compounds. The thickness of the oxide layer of the Ti6Al4V increased from 59.55 μm to 139.15 μm. In contrast, with the addition of Y2O3, the thickness of the oxide layer increased from 35.73 μm to 80.34 μm. This indicates that the thickness of the oxide layer formation was a diffusion-controlled process and, therefore, the thickness of the oxide layer increased with an increase in temperature. The Ti6Al4V-1.0 wt.% Y2O3 alloy exhibits excellent oxidation resistance, and the thickness is significantly lower than that of the Ti6Al4V alloy. The oxidation kinetics of the Ti6Al4V and Ti6Al4V-1.0 wt.% Y2O3 alloys at 600 °C and 800 °C follows a parabolic rule, whereas the oxidation of the Ti6Al4V and Ti6Al4V-1.0 wt.% Y2O3 alloys at 1000 °C follows the linear law. The average microhardness values of Ti6Al4V samples after oxidation increased to 818.9 ± 20 HV0.5 with increasing temperature, and the average microhardness values of the Ti6Al4V-1.0 wt.% Y2O3 alloy increases until 800 °C and then decreases at 1000 °C. The addition of Y2O3 shows a significant improvement in the microhardness during the different temperatures after oxidation.

Multiaxial fatigue life prediction based on modular neural network pretrained with uniaxial fatigue data

PurposeData-driven models are increasingly being used to predict the fatigue life of many engineering components exposed to multiaxial loading. However, owing to their high data requirements, they are cost-prohibitive and underperforming for application scenarios with limited data. Therefore, it is essential to develop an advanced model with good applicability to small-sample problems for multiaxial fatigue life assessment.Design/methodology/approachDrawing inspiration from the modeling strategy of empirical multiaxial fatigue models, a modular neural network-based model is proposed with assembly of three sub-networks in series: the first two sub-networks undergo pretraining using uniaxial fatigue data and are then connected to a third sub-network trained on a few multiaxial fatigue data. Moreover, general material properties and necessary loading parameters are used as inputs in place of explicit damage parameters, ensuring the universality of the proposed model.FindingsBased on extensive experimental evaluations, it is demonstrated that the proposed model outperforms empirical models and conventional data-driven models in terms of prediction accuracy and data demand. It also holds good transferability across various multiaxial loading cases.Originality/valueThe proposed model explores a new avenue to incorporate uniaxial fatigue data into the data-driven modeling of multiaxial fatigue life, which can reduce the data requirement under the promise of maintaining good prediction accuracy.