Modern engineered systems generally work under complex operational conditions. However, most of the existing artificial intelligence (AI)-based prognostic methods still lack an effective model that can utilize operational conditions data for remaining useful life (RUL) prediction. This paper develops a novel prognostic method based on Bi-Directional Long Short-Term Memory (BLSTM) networks. The method can integrate multiple sensors data with operational conditions data for RUL prediction of engineered systems. The proposed architecture based on BLSTM networks includes three main parts: 1) One BLSTM network is used to directly extract features hidden in the multiple raw sensors signals; 2) another BLSTM network is employed to learn higher features from operational conditions signals and the learned features from the sensors signals; 3) fully connected layers and a linear regression layer are stacked to generate the target output of the RUL prediction. Unlike other AI-based prognostic methods, the developed method can simultaneously model both sensors data and operational conditions data in a consolidated framework. The proposed approach is demonstrated through a case study on aircraft turbofan engines, and comparisons with other existing state-of-the-art methods are also presented.

Fault tree analysis (FTA) is one of the most popular failure analysis techniques that reveal the potential pathways leading to systems or components failure. It has been widely employed in numerous sectors to understand how a system fails and is improved. However, the conventional FTA has been criticized due to a series of inherent shortcomings in the FTA state of the arts. Accordingly, scholars, engineers, and practitioners made their attempts to improve the FTA by dealing with its critical deficiencies over the last decade. However, a few works have been performed to review and synthesize the relevant studies on FTA improvement topics. Thus, the present study is aimed to carry out a systematic literature review of the state‐of‐the‐art theoretical and empirical findings concerning FTA improvement from 2011 to 2021 using the Scopus database collection. In this sense, an in‐depth investigation is conducted using statistical metadata analysis. This subject discusses frontier directions and development trends to reveal the research status. In addition, a bibliometric study is undertaken to ascertain the most productive and influential researchers, research centers, and hotspot fields. It also sheds light on the FTA shortcomings in the existing literature, the evolution in FTA improvement topics, and research opportunities. The outcomes of the present work highlighted that the annual publications on FTA improvement topics are significantly growing, especially after 2019. Besides, Jianxiu Wang, Yan‐Feng Li, and Yihuan Wang are the most productive, prolific, and highly cited authors worldwide; and Asia, particularly China, is the leading contributor in the FTA area. According to Bradford's law, one‐third of all publications (7995) in the field of FTA improvement have been published by 40 sources. Finally, “Decision‐making,” “Risk analysis,” “Uncertainty Analysis,” and “Bayesian Networks” are the four major hot topics integrated into improving the conventional FTA.

A new mean stress corrected strain energy model is proposed for fatigue life prediction of metals. Specifically, a mean stress sensitivity parameter is incorporated into modify the dissipated strain energy by introducing two mean stress correction factors. The prediction accuracy of the proposed model is compared with those of Walker, Smith–Watson–Topper, Morrow, and generalized damage parameter models by using 13 experimental data sets. All data points for each material are, respectively, fitted into a single mean stress corrected strain energy-life curve. More accurate predictions are achieved by the proposed model for all data sets with lower model prediction errors than others.

This paper presents a modified nonlinear fatigue damage accumulation model accounting for load interaction effects. The original model is based on physical property degradation of materials, from which the load interaction effects are ignored. However, the load interaction effects have a significant influence on the fatigue life. In the study, by analyzing five damage models, a load interaction parameter is obtained and added to the original model. Experimental work is then carried out to verify the modified model of four categories of experimental data from smooth and notch specimens under two-level stress loading. Moreover, comparison is made among the results calculated by the test data, the Miner’s rule, the original model, and the modified model.