Classical machine elements have been around for centuries, even millennia. However, the current advancement in Structural Health Monitoring (SHM), together with Condition Monitoring (CM), requires that machine elements should be upgraded from a not-simple object to an intelligent object, able to provide information about its working conditions to its surroundings, especially its health. However, the integration of electronics in a mechanical component may lead to a reduction in its load capacity since the component may need to be modified in order to accommodate them. This paper describes a case study, where, differently from other cases present in the literature, sensor integration has been developed under the gear teeth of an actual case-hardened helical gear pair to be used within an actual gearbox. This article has two different purposes. On the one hand, it aims to investigate the effect that component-level SHM/CM has on the gear load carrying capacity. On the other hand, it also aims to be of inspiration to the reader who wants to undertake the challenges of designing a sensor-integrated gear.

Monitoring systems for rolling contacts in machinery are widespread. There are multiple solutions in various applications like Health Usage Monitoring Systems (HUMS) for Helicopters and smart bearings from different manufacturers. The number of solutions and possibilities is rising. This paper outlines how the vibrational behavior depends on the measuring position outside and inside the gearbox. The effect of the sensor location is evaluated by examining different locations close to the main excitation of gearboxes—the loaded tooth contact—as well as positions on the gearbox housing. Based on the results, recommendations for an optimal sensor position for gear vibration monitoring are given by considering the efforts of sensor integration. The results can be used to select sensors with the lowest cost to support the widespread gear vibration monitoring.Important locations for health monitoring are the gear meshes inside the gearbox. Due to the requirement of high power density, a compact design is mandatory. This does not allow for sensor application close to the gear meshes but only on the outside of the gearbox. An impediment of signal quality and less chance of early damage detection is the consequence. Hence, efforts have been made to directly integrate multiple sensors inside the gear body without negatively impacting the package.For the investigation of the vibration transmission behavior, an FZG gear test rig is selected. These standardized test rigs are approved and established all around the world for the creation and evaluation of various gear failure data. The presented test rig has been modified to be able to sense vibration in the gear wheel, at the gear wheel, and on the gearbox housing to evaluate different sensor positions and vibration sensors for their suitability on vibration measurement.

The effective diagnosis of gear faults significantly reduces downtime and cost and enhances the reliability of rotating machines such as wind turbines. In recent years, deep learning models have been increasingly applied in gear diagnostics at the cost of high expertise. Concurrently, it is important for deep learning models to extract features in accordance with physical phenomena to achieve a robust and reliable diagnostic performance. In this study, we constructed a multi-task diagnostic transformer model that focuses on the physical phenomena of gear fault vibrations. The tasks of estimating rotational shaft speed and gear mesh frequency (GMF) were simultaneously performed along with the diagnostic task. The proposed model was verified using acceleration data from an in-house gear test rig and five public datasets, under various operating conditions and gear geometries. The results show that multi-task learning (MTL) improves the diagnostic performance of gear faults in untrained conditions. Furthermore, we visualized the significant points of the input acceleration waveforms for the diagnostic results using explainable AI (XAI). The results showed that the proposed method allows periodic fault vibrations, in accordance with the physical phenomena of gears, to contribute more robustly to diagnosis.

Defects in machine components can result in costly machine downtime. Sensors are widely deployed to prevent this, and intelligent monitoring systems are implemented. However, these solutions are often custom-made, expensive, and difficult to integrate. Technological advances have enabled the development of small, inexpensive sensors and microcontrollers that can be integrated into smaller components. Integrating these into standard machine elements allows modular monitoring systems with sensors close to the vibration source. This paper presents a sensor-integrated gear called SIZA (German abbreviation: “Sensorintegrierendes Zahnrad”, sensor-integrating gear), which incorporates different sensors and a microcontroller, along with software capable of detecting damage and fatigue and communicating this information to a nearby supervisory master system. The electronic system is housed in customized cavities within the gear body, located directly beneath the teeth, with minimal structural weakening. Since the outer dimensions of the gear remain unchanged, it can be used in various systems. Two generations of prototypes have been developed, and the development process and component selection, including benchmarking, are detailed in this paper. Additionally, customized software has been designed to minimize the microcontroller’s energy consumption and computational time, enabling autonomous wireless monitoring. The experimental measurements show the capabilities and advances of sensors close to tooth contact, which is the source of excitation and heat during gear operation. The SIZA is equipped with temperature sensors at multiple positions, accelerometers, microphones, and a hall sensor to provide a comprehensive overview of the gear operation. The temperature sensors give information about absolute temperatures, temperature gradients, and lubrication thickness in the loaded contact. The vibration sensors characterize the vibration behavior of the gear during operation, such as rotating frequencies, gear mesh frequency, and damage-caused frequency amplitudes. The hall sensor is also considered for the measurement of rotating speed in order to evaluate the operation condition and to estimate number of load cycles, which have already been performed. The prototype was developed and built collaboratively by the Institute of Machine Elements (FZG), the Institute of Automation and Information Systems (AIS), and the Chair of Circuit Design (LSE) at the Technical University of Munich (TUM).

Condition monitoring systems are widely used in gearboxes. Gears are one of the most crucial components for power transmission. Hence, the optimal sensor positions for condition monitoring of gears should be investigated to maximize reliability and to minimize costs. This work aims to analyze measured signals from rotating sensors at gears and compare them to signals from housing sensors to find the suitable positions for condition monitoring of the gears. Additionally, the rotational speed and external torque influences on the signal quality have been investigated. These are compared with a simulation model, which considers the vibration excitation from the gear mesh and bearings. The results show that the rotational speed affects the amplitude of the excitation. On this basis, we also investigate the amplitudes of the excitation frequencies of interest. The ratio of the amplitudes of these frequencies related to the mean values of the measurement signals is called the peak-to-mean ratio (PMR), and this PMR corresponds to the speed which is of interest for automatic fault detection in the gearboxes. Additionally, the simulation results show that the intensity of the vibration with the gear mesh frequency hardly reduces during transmission through the tapered roller bearings.