Health monitoring is the tracking of any aspect of a structure's health by reliably measured data and analytical simulations in conjunction with heuristic experience so that the current and expected future performance of the machine for, at least the most critical limit events, can be described in a proactive manner. Advanced intelligent condition monitoring and fault diagnosis methods, together with abundant measuring information, greatly enhance the performance of rotating mechanical systems. Although a lot of research has been carried out for developing a method for determining the health of machines using data-based techniques, it is still challenging to accurately determine the remaining useful life (RUL) because the degradation process is extremely complex and stochastic. Classical statistical features obtained from the raw vibration signal fail to hold understanding and steadiness for fault detection, exclusively in multifaceted noisy situations. A proper application and integration of big data analytics, signal processing methods, measurement systems, fast computing, and machine learning can lead to the development of accurate diagnosis and prognosis methods of mechanical systems for industrial applications.

Despite a lot of advancements in the area of signal processing and condition monitoring methods, the modern industry can face challenges while developing accurate health monitoring solutions. There is limited labeled data about machine health and the methods work satisfactorily on the machines on which training is done. However, as soon as the operating conditions such as loading and operating speed change, the methods lose their accuracy. The most important is that the industrial environment doesn’t allow much research.

To rapidly report and spread the latest advancements in the science of fault diagnosis and detection, including new discoveries and valuable applied research from all over the world, this Special Issue aims to gather state-of-the-art original research and review articles covering all aspects of theoretical and applied investigations about the latest development of sensor technologies and measurement methods for the detection of defects and diagnosis of faults.

Potential topics include but are not limited to the following:

• Machine learning methods in the area of condition monitoring
• Deep Learning in the area of condition monitoring of mechanical systems
• Defect severity estimation
• RUL Estimation
• Simulation-based condition monitoring
• Vibro-acoustic diagnosis of machinery
• Case studies and industrial applications