Purpose This review underscores the importance of reliability, availability, maintainability (RAM) + analysis in assessing system performance and safety parameters while identifying risk-based improvements. The insights, gaps, and tendencies identified serve as foundation for future improved research studies and applications in this topic. Design/methodology/approach This study presents a systematic literature review (SLR) on RAM analysis methodologies and derivations (especially RAMI, RAMS, and RAMSS), their applications, and research gaps across several engineering domains. To address different methodological derivations, the term “RAM+” is proposed. The review follows a well-established SLR framework, covering planning, searching, data collection, analysis, synthesis, interpretation, reporting, and review updating activities. These activities resulted in the selection of 100 articles, based on predefined inclusion and exclusion criteria. Findings The analysis reveals a wide range of techniques applied in RAM + studies, including functional analysis, failure mode and effects analysis (FMEA)/failure mode, effects, and criticality analysis (FMECA), reliability block diagrams (RBD), Markov models, fault tree analysis, Petri nets, Poisson processes, Bayesian models, and Monte Carlo methods. Among these, RBD was the most widely used tool for system, subsystem or component performance modeling technique, while functional analysis and FMEA/FMECA were the most common descriptive methods. A critical gap was identified in validation practices, with few studies incorporating validation procedures. Corrective maintenance was identified as the dominant maintenance strategy. Sensitivity analysis was frequently performed, with input parameter sensitivity being the most commonly applied approach. Most studies relied on third-party databases for input data. The findings also highlight the widespread adoption of RAM + analysis across multiple industries, with nuclear fusion emerging as the most prominent application domain. RAM + methodologies are often applied in hybrid approaches, demonstrating their adaptability to diverse engineering challenges. Research limitations/implications A critical gap was identified in validation practices, with a few studies incorporating validation procedures. Corrective maintenance was identified as the dominant maintenance strategy. Sensitivity analysis was frequently performed, with input parameter sensitivity being the most applied approach. Practical implications The findings also highlight the widespread adoption of RAM + analysis across multiple industries, with nuclear fusion emerging as the most prominent application domain. RAM + methodologies are often applied in hybrid approaches, demonstrating their adaptability to diverse engineering challenges. This review underscores the importance of RAM + analysis in assessing system performance and safety parameters while identifying risk-based improvements. The insights, gaps, and tendencies identified serve as foundation for future improved research studies and applications in this topic. Originality/value This study presents a systematic literature review (SLR) on reliability, availability, maintainability (RAM) analysis methodologies and derivations (especially RAMI, RAMS, and RAMSS), their applications, and research gaps across several engineering domains.
Purpose The current study proposes building a strong predictive maintenance (PdM) model for industrial systems through the use of ensemble machine learning models to forecast equipment failures before they happen. The research emphasizes enhancing the reliability during operation, minimizing downtime and offering a scalable solution to fill the gap between theoretical studies and real-world industrial applications in the Industry 5.0 era. Design/methodology/approach Two benchmark datasets: AI4I 2020 and its extended variant AI4I Predictive Maintenance Dataset with Irregularities (PMDI) are employed to verify the proposed approach. The research undertakes thorough data pre-processing, such as label encoding, feature scaling and Synthetic Minority Over-sampling Technique for handling class imbalance and data quality problems. Three heavy-hitting gradient boosting algorithms: XGBoost, LightGBM and CatBoost are employed as base learners in a stacking ensemble, with logistic regression as the meta-learner. The performance of the model is tested rigorously by Accuracy, Precision, Recall, F1-score and Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). Findings Experimental results indicate that stacking ensemble outperforms standalone base models consistently and attains 99.16% accuracy for the AI4I 2020 dataset and 99.60% accuracy for the AI4I PMDI dataset with ROC-AUC values close to 0.99. These results validate the success of ensemble learning, especially stacking, in achieving high accuracy and reliability for industrial PdM applications. Research limitations/implications The present study is restricted to publicly available benchmark datasets and artificial industrial settings. Real-time deployment, integration with deep models like CNN, BiLSTM or Transformers, and addition of cost-sensitive measures or explainability tools like SHAP and LIME for increased interpretability and usability are potential future extensions. Originality/value This research combines three gradient boosting models into a stacked ensemble framework designed specifically for PdM in an innovative way. It adds a reproducible, understandable and highly performant PdM model with practical industrial benefit, research relevance and social impact that supports Industry 5.0-compatible and sustainable data-based maintenance practices.
Purpose This study aims to develop a modified cumulative damage sequential preventive maintenance (CDSPM) model that addresses the limitations of traditional cumulative shock sequential models by incorporating three realistic factors often ignored in maintenance planning: prior damage in used machines, shock dampening effects and non-constant shock magnitudes. The research seeks to provide a more practical decision-making tool for industries, particularly in developing countries, that rely heavily on fairly-used equipment exposed to complex shock environments. Design/methodology/approach The study modifies the existing CDSPM model by introducing a non-zero initial damage state (R0 > 0), a shock dampening factor αl which is defined as the proportion of shock damage absorbed by the machine. This provides a mathematical mechanism for representing the protective effect of built-in shock-resistance components. The effective shock damage transmitted to the machine is represented by 1-αl100% with 0⩽αl⩽1. This formulation distinguishes between the physical magnitude of an external shock and the actual damage transmitted to the machine. It therefore provides a theoretical basis for incorporating mechanical protection into stochastic reliability models rather than assuming that the entire shock magnitude contributes directly to cumulative damage. Also, the Gamma-distributed shock magnitudes replace the traditional exponential distribution. The modified model formulates total expected cost functions for both infinite and finite time horizons, derives optimality conditions using Lagrange optimization, and develops a comprehensive availability model. The methodology is validated through application to a used Caterpillar 320BL hydraulic excavator using empirical field data, with the algorithm implemented in Python programming language. Findings The modified CDSPM model demonstrates that accounting for prior damage and shock resistance leads to shorter, effective and more realistic maintenance intervals with lower expected maximum cost rate compared to classical models. The optimal policy recommends P* = 12 maintenance intervals with a maximum expected cost rate of 26.99 million Naira and system availability of 98.51%, whereas the classical model (assuming pristine condition) suggests P** = 14 intervals with 58.98 million Naira cost and 99.18% availability for the case study used Caterpillar excavator. The 15% reduction in intervals and significantly lower lifecycle costs confirm the fact that classical models overestimate equipment longevity and underestimate maintenance requirements for fairly-used machines. Research limitations/implications The model's parameters are estimated from a single machine type and operational context, which may limit generalizability. The assumption of a constant shock dampening factor and fixed improvement factor may not capture all operational complexities. These identified baseline conditions are essential for real-world model development. Therefore, future research should explore time-varying dampening factors, multiple failure mechanisms and application to diverse equipment types across different industrial sectors. Practical implications The modified CDSPM model provides maintenance planners with a practical tool for scheduling sequential preventive maintenance (PM) on used equipment, enabling more accurate prediction of maintenance intervals, cost optimization and availability estimation that could not have been appropriate with fixed interval PM. The approach helps reduce unplanned failures, minimize downtime and extend equipment life through evidence-based decision-making that reflects actual machine conditions. Social implications By improving cumulative damage sequential maintenance practices for fairly-used equipment, particularly in developing countries where second-hand machinery is prevalent, the model supports sustainable industrial operations, reduces resource waste and enhances productivity and workers' safety through more reliable equipment performance. This cost-effective maintenance strategy contributes to economic efficiency in resource-constrained environments. Originality/value This research presents an integrated CDSPM model that simultaneously incorporates prior damage, shock dampening and Gamma-distributed shock magnitudes. The work extends Nakagawa and Mizutani’s (2008) foundational model as a special case while providing a more realistic model for used equipment maintenance. The availability model and finite horizon optimization approach offer novel contributions to reliability engineering practice.
This paper develops a unified framework for preventive maintenance (PM) modelling that simultaneously accounts for downtime severity and interval-dependent effectiveness. The aim is to generate maintenance policies that are both risk-aware and operationally efficient for repairable industrial systems with multiple PM types. Downtime-based severity weights are embedded within a virtual-age non-homogeneous Poisson process (NHPP) with multiple PM types. Interval-dependent restoration factors are estimated non-parametrically using interval discretisation and isotonic regression. Model parameters are obtained by severity-weighted maximum pseudo-likelihood using global metaheuristics and local refinement. Where within-interval variation is weak, conservative constant restoration estimates are used in the constrained availability optimisation. Optimised schedules are compared with original equipment manufacturer (OEM) baseline policies. All three optimisation algorithms favour PM intervals near the upper operational bounds. Under severity weighting, the best schedule, approximately (298.5, 547.2, 1000) h, increases availability from 0.7368 to 0.7513. The light (Type I) PM interval has the greatest influence on availability, while major (Type III) PM timing is comparatively insensitive. Severity-aware calibration also improves model fit relative to the unweighted baseline when evaluated under the severity-weighted pseudo-likelihood objective. The dataset is limited to one subsystem and four trucks, and severity is represented solely by downtime. Sparse PM observations constrain recovery of detailed non-parametric restoration profiles, particularly for the less frequent PM types. Broader fleets, richer severity measures and hierarchical treatment of fleet heterogeneity would strengthen inference, permit fuller estimation of interval-dependent restoration and improve generalisability. For the studied fleet, severity-aware calibration combined with interval-effectiveness diagnostics supports longer PM intervals within the tested operational bounds, reducing planned downtime and increasing availability. Scheduling precision should be concentrated on moderate PM, which exerts the greatest influence on availability, while major PM can be scheduled more flexibly. The framework also provides practitioners with a data-driven means of testing whether maintenance effectiveness varies materially with intervention timing. This study is the first to jointly integrate downtime-based failure severity, interval-dependent restoration and multiple PM types within a non-parametric NHPP virtual-age framework. It links severity-aware parameter estimation with constrained availability optimisation while retaining the interpretability of classical imperfect-maintenance models, providing a bridge between risk-sensitive reliability modelling and implementable industrial maintenance policy.
This study develops and validates an autonomous maintenance (AM) implementation and sustainability framework for sewing operations in the garment manufacturing industry, where labor-intensive production and limited operator maintenance time constrain conventional AM implementation. A qualitative framework development approach was adopted. An initial framework was developed through a structured literature review and refined through semi-structured interviews with twelve garment manufacturing experts from Sri Lanka, Bangladesh, Indonesia, and Kenya. Interview data were analyzed using thematic analysis. Six refinement themes emerged from the study: impactful abnormality identification, operator time constraints, comprehensive inspection, training and awareness, performance monitoring, and management governance. These informed a six-stage framework integrating abnormality management, layered inspections, digital performance monitoring, and governance mechanisms to support sustainable AM implementation. The framework was developed based on qualitative insights from experts across South Asia, Southeast Asia, and East Africa. Future research should focus on empirically validating the framework across diverse manufacturing contexts. The framework provides manufacturers with a structured approach for implementing and sustaining AM while maintaining production efficiency. Improved operator involvement enhances equipment awareness, safer machine operation, and workforce capability. The study contributes an expert-validated AM framework that adapts established AM principles to the operational realities of sewing operations in the garment manufacturing industry. Its originality lies in explicitly addressing operator time constraints and integrating AM implementation with routine production practices and sustainability mechanisms.
