The precise maintenance and scientific management of large and complex mechanical equipment are of great significance for ensuring the safe operation of equipment and improving economic efficiency. Prognostics and health management (PHM), as an advanced method of equipment maintenance and management, has received widespread attention. Remaining useful life (RUL) prediction is one of the key technologies of PHM and has become a research hotspot and challenge in the field of equipment PHM. Firstly, PHM and its key technology, i.e., RUL prediction, are briefly introduced. Its approaches are divided into statistical model-based approaches, artificial intelligence (AI) approaches, physics model-based approaches and hybrid prognostic approaches. Then, the development branches and the current research status of each type of approaches are sorted out, and the corresponding advantages and disadvantages are summarized. Finally, the future technological development direction and challenges faced are analyzed, providing some reference for the development and application of PHM in the future, as well as in-depth research on RUL prediction approaches.

Gearbox is an important structure of rotating machinery, and the accurate fault diagnosis of gearboxes is of great significance for ensuring efficient and safe operation of rotating machinery. Aiming at the problem that there is little common compound fault data of gearboxes, and there is a lack of an effective diagnosis method, a gearbox fault simulation experiment platform is set up, and a diagnosis method for the compound fault of gearboxes based on multi-feature and BP-AdaBoost is proposed. Firstly, the vibration signals of six typical states of gearbox are obtained, and the original signals are decomposed by empirical mode decomposition and reconstruct the new signal to achieve the purpose of noise reduction. Then, perform the time domain analysis and wavelet packet analysis on the reconstructed signal, extract three time domain feature parameters with higher sensitivity, and combine them with eight frequency band energy feature parameters obtained by wavelet packet decomposition to form the gearbox state feature vector. Finally, AdaBoost algorithm and BP neural network are used to build the BP-AdaBoost strong classifier model, and feature vectors are input into the model for training and verification. The results show that the proposed method can effectively identify the gearbox failure modes, and has higher accuracy than the traditional fault diagnosis methods, and has certain reference significance and engineering application value.

Whether in the design and manufacturing stage of complex equipment, or in its operation and maintenance stage, equipment reliability is a key indicator. In order to improve and maintain the reliability of equipment, using FMECA method to determine the key components of equipment is an important foundation. To solve the problem of determining the key components of a complex reciprocating mechanical system, this paper proposes an improved FMECA method based on an adaptive weighted information fusion model, on the basis of the fuzzy FMECA method. By constructing an initial weight judgment support matrix, the weights of different information sources are determined, and the weight results of each influence factor are obtained. Finally, the comprehensive criticality of each fault mode is calculated to rank the importance of each component. The effectiveness of the proposed method was verified using a complex reciprocating mechanical system as an example.