Visual inspection remains a cornerstone of quality control in welded structures, yet manual evaluations are inherently constrained by subjectivity, inconsistency, and limited scalability. This study presents WeldVGG, a deep learning-based visual inspection model designed to automate weld defect classification using radiographic imagery. The proposed model is trained on the RIAWELC dataset, a publicly available collection of X-ray weld images acquired in real manufacturing environments and annotated across four defect conditions: cracking, porosity, lack of penetration, and no defect. RIAWELC offers high-resolution imagery and standardized class labels, making it a valuable benchmark for defect classification under realistic conditions. To improve trust and explainability, Grad-CAM++ is employed to generate class-discriminative saliency maps, enabling visual validation of predictions. The model is rigorously evaluated through stratified cross-validation and benchmarked against traditional machine learning baselines, including SVC, Random Forest, and a state-of-the-art architecture, MobileNetV3. The proposed model achieves high classification accuracy and interpretability, offering a practical and scalable solution for intelligent weld inspection. Furthermore, to prove the model’s ability to generalize, a test on the GDXray was performed, yielding positive results. Additionally, a Wilcoxon signed-rank test was conducted separately to assess statistical significance between model performances.

The effectiveness of a comprehensive maintenance and reliability management process can be assessed through an in-depth analysis of various factors that collectively represent the maintenance contribution to the operational and production processes of an industrial asset. There are no simple formulas for designing an integrated maintenance and reliability model within an asset management framework (in accordance with the ISO 55001 standard), nor are there fixed or universal rules that apply equally to all production assets over time. In light of this, the primary goal of this article is to provide an overview of the implementation project of the AMORMS (Asset Management, Operational Reliability and Maintenance Survey), based on the maintenance management model (MMM) developed by INGEMAN, at the SINEA PERU plant, a leading company in Latin America specializing in the industrial production of recycled plastic containers for commercial beverages (PET preforms—Polyethylene Terephthalate). Lastly, the article outlines the recommendations and high-impact action plans that will support SINEA PERU in strengthening the efficiency of its maintenance and reliability management processes while effectively optimizing the value of its industrial assets throughout its life cycle.

This research examines how Industry 4.0 technologies such as artificial intelligence (AI), the Internet of Things (IoT), and digital twins (DT) are used in the digital transformation process of warranty management. This research focuses on converting traditional warranty management practices from reactive systems to predictive and proactive ones, improving operational performance and customer experiences. Based on an already established eight-phase framework for warranty management, this paper reviews machine learning (ML), natural language processing (NLP), and predictive analytics, among other advanced technologies, to enhance warranty optimization processes. Best practices in the automotive sector, as well as in the railway and aeronautics industries, have experienced substantial achievements, including optimized resource utilization and savings, together with tailored services. This study describes the limitations of capital investments, labor training requirements, and data protection issues. Therefore, it suggests implementation sequencing and staff education approaches as solutions. In addition to the current evolution of Industry 4.0, this research’s conclusion highlights how digital warranty management advancements optimize resources and reduce costs while adhering to international standards and ethical data practices.

Human reliability and human error are factors that are present in all areas: industrial, economic, social, etc. All these areas require to a greater or lesser extent a physical and mental effort to satisfy their own needs, those of others, or established requirements that, depending on the circumstances and the nature of the person, can lead to errors. Certainly, it is not possible to find a single human reliability method that can meet all the expectations and technical demands related to the analysis of human errors. However, it is important to note that the orientation of all human reliability methods is focused on the study and analysis of the risk factor (frequency by consequences). In other words, as can be observed throughout this chapter, all human reliability methodologies seek to help us reduce the uncertainty in the process of evaluating the frequencies of unforeseen events (human errors) and the consequences that such human errors can bring to safety, the environment, and the operations within the framework of an industrial production process. Request access from your librarian to read this chapter's full text.

The chapter explains in detail the maintenance management model (MMM) taken as a reference for the development of the book. The chapter is based on the eight phases of the MMM. The first three blocks determine the effectiveness of the management; the following blocks assure the same efficiency and continuous improvement in the following way: Blocks 4 and 5 include actions for the planning and scheduling of maintenance, including, of course, the capacity of planning of department of maintenance. Blocks 6 and 7 are dedicated to the evaluation and control of the maintenance and the cost of assets throughout their life cycle. This chapter of introduction briefly summarizes the process and the reference frame necessary for the implementation of the MMM. This chapter also presents the relationship between the eight phases of the maintenance management model proposed and the general requirements of the asset management standard ISO 55000 to show how the gradual implementation of the MMM largely covers the requirements of the standard ISO 55000.

The techniques of criticality analysis are tools that allow identifying and hierarchy for their importance the assets of an installation on which it is worth directing resources (human, economic, and technological). In other words, the process of criticality analysis helps determine the importance and consequences of potential failure events of production systems within the operational context in which they perform. Taking as reference the maintenance management model (MMM) of the eight phases, this chapter related to techniques of prioritization and criticality is part of Phase 2 of the MMM. In the following chapter, the most important theoretical aspects of equipment hierarchical analysis techniques are explained, based on the qualitative and quantitative risk model (failures frequencies and consequences). Finally, two case studies in the oil refining industry are developed; the first case uses the tool qualitative risk matrix (QRM), and the second case uses the tool risk analytic hierarchy process (RAHP).