Machine learning techniques have progressively emerged as important and reliable tools that, when combined with machine condition monitoring, can diagnose faults with even superior performance than other condition-based monitoring approaches. Furthermore, statistical or model-based approaches are often not applicable in industrial environments with a high degree of customization of equipment and machines. Structures such as bolted joints are a key part of the industry; therefore, monitoring their health is critical to maintaining structural integrity. Despite this, there has been little research on the detection of bolt loosening in rotating joints. In this study, vibration-based detection of bolt loosening in a rotating joint of a custom sewer cleaning vehicle transmission was performed using support vector machines (SVM). Different failures were analyzed for various vehicle operating conditions. Several classifiers were trained to evaluate the influence of the number and location of accelerometers used and to determine the best approach between specific models for each operating condition or a single model for all cases. The results showed that using a single SVM model with data from four accelerometers mounted both upstream and downstream of the bolted joint resulted in more reliable fault detection, with an overall accuracy of 92.4%.

The main objective of this study is to evaluate residual stresses in AISI 316L and 18Ni Maraging 300 functionally graded materials with continuous variation of composition within a single layer using the contour method. The manufacture of this kind of layer-level continuous functionally graded materials by employing a Powder Bed Fusion-Laser Beam system utilizing a blade/roller-based powder spreading technique has only been recently devised and a proper residual stress analysis is still required. In fact, as the mechanical properties of additively manufactured samples are significantly influenced by the direction of construction, the same holds true for the direction along which the compositional variation is made. Furthermore, in this study, the impact of solution annealing and aging heat treatment, which are necessary for enhancing the mechanical properties of martensitic steel, on residual stresses was explored. Additionally, the effect of adopting material-differentiated process parameters was investigated. The results indicated that each specimen displayed areas of tensile stress concentration on the upper and lower surfaces, balanced by compression in the center. The application of heat treatment led to a decrease in the maximum tensile stress of 8% and provided a uniform and significant stress reduction within the maraging steel. Finally, the implementation of material-specific process parameters for the three composition zones in conjunction with the heat treatment resulted in a reduction in the maximum residual stress of 35% and also a significantly lower residual stress field throughout the specimen.

Bolt loosening in industrial vehicles poses substantial safety and operational risks, highlighting the need for reliable monitoring systems. Despite progress in diagnostic techniques, research specifically focused on detecting bolt loosening in complex rotating joints remains limited. This study introduces a novel approach that integrates vibration analysis with deep learning to enhance fault detection in bolt loosening in a rotating joint of a custom sewer cleaning vehicle transmission. The method uses kurtogram-based frequency domain analysis to convert vibration signals into images, which are then processed using a customized convolutional neural network (CNN). This approach eliminates the need for manual feature extraction and enhances diagnostic reliability. The results indicate that a single accelerometer (sensor A1) outperforms multi-sensor configurations. Furthermore, measurements from the accelerometer showed the highest accuracy, demonstrating that longitudinal vibrations are the most reliable for detecting bolt loosening. This study contributes to predictive maintenance and intelligent fault detection, offering a scalable, high-performance solution for monitoring bolt loosening. The integration of kurtogram-based spectral analysis and deep learning paves the way for next-generation autonomous fault detection systems, capable of real-time deployment in dynamic and complex industrial settings.

This study aims to propose a thorough experimental methodology to assess the mechanical quality of dissimilar joints. This comprehensive approach investigates the fatigue behavior by exploiting the thermographic method, accompanying and correlating the results with information obtained from extensive measurements of residual stresses and detailed evaluation of fracture surfaces. The integration of the information obtained by this hybrid approach allows for a deeper understanding in terms of fatigue behavior even in complicated situations as those represented by dissimilar welded joints. A complex laser-welded Ti6Al4V/Inconel 625 dissimilar joint, obtained using intermediate inserts of Vanadium and AISI 304, was considered as case study. The residual stresses, both longitudinal and transverse to the weld beads, were measured on surface by means of X-ray diffraction, whereas, for in-depth measurements, the multiple-cut contour method was implemented to determine full 2D maps of longitudinal residual stresses with the first cut, and transverse stresses in the Vanadium insert with the second cut. In the investigation of longitudinal residual stresses, the area mostly affected by harmful tensile residual stresses is the weld between the stainless steel and Vanadium, where the maximum value of about 560 MPa is reached; the analysis of transverse residual stresses highlighted a maximum value of 350 MPa at the core of the Vanadium insert. The fatigue behavior of the joints was investigated along with a detailed analysis of the fractured surfaces by scanning electron and confocal microscopes. The analysis of the fracture surfaces indicated that the failure modes are mainly related to the occurrence of defects on the crack path, especially at stress range higher than 200 MPa, for which a large number of pores cluster were detected. Nevertheless, the crack initiation is usually on the side of Vanadium. When the crack path deviates on the stainless-steel region, the fracture mode is brittle due to high residual stresses.