With the tremendous revival of artificial intelligence, predictive maintenance (PdM) based on data-driven methods has become the most effective solution to address smart manufacturing and industrial big data, especially for performing health perception (e.g., fault diagnosis and remaining life assessment). Moreover, because the existing PdM research is still in primary experimental stage, most works are conducted utilizing several open-datasets, and the combination with specific applications such as rotating machinery is especially rare. Hence, in this paper, we focus on data-driven methods for PdM, present a comprehensive survey on its applications, and attempt to provide graduate students, companies, and institutions with the preliminary understanding of the existing works recently published. Specifically, we first briefly introduce the PdM approach, illustrate our PdM scheme for automatic washing equipment , and demonstrate the challenges encountered when we conduct a PdM research. Second, we classify the specific industrial applications based on six algorithms of machine learning and deep learning (DL), and compare five performance metrics for each classification. Furthermore, the accuracy (a metric to evaluate the algorithm performance) of these PdM applications is analyzed in detail. There are some important conclusions: 1) the data used in the summarized literature are mostly from public datasets, such as case western reserve university (CWRU)/intelligent maintenance systems (IMS); and 2) in recent years, researchers seem to focus more on DL algorithms for PdM research. Finally, we summarize the common features regarding our surveyed PdM applications and discuss several potential directions.

Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey

Prognostics of the remaining useful life (RUL) has emerged as a critical technique for ensuring the safety, availability, and efficiency of a complex system. To gain a better prognostic result, degradation information is quite useful because it can reflect the health status of a system. However, due to the lack of accurate information about the plants’ degradation, the prognostic model is usually not well established. To solve this problem, this paper proposes a two-stage strategy that is in the context of data-driven modeling to predict the future health status of a bearing, where the degradation information was estimated by calculating the deviation of multiple statistics of vibration signals of a bearing from a known healthy state. Then, a prediction stage based on an enhanced Kalman filter and an expectation–maximization algorithm were used to estimate the RUL of the bearing adaptively. To verify the effectiveness of the proposed approach, a real-bearing degradation problem was implemented.

A Two-Stage Data-Driven-Based Prognostic Approach for Bearing Degradation Problem

A degradation path-dependent approach for remaining useful life estimation with an exact and closed-form solution

Batteries are prevalent energy providers for modern systems. They can also be regarded as storage units for renewable and sustainable energy. Failures of batteries can bring huge losses in terms of personnel, facility, environment, and reputation aspects. Therefore the accurate health estimation and high availability of batteries is urgently required by corresponding users, distributors, and manufactures. Fortunately, prognostics and health management (PHM) technique has been demonstrated the capability of supporting the improvement of the availability and reliability of batteries. In this paper, we gave a review on the state-of-the-art of the PHM study on batteries. We observed the increase of publication related to battery PHM in the past decade (2009–2018), especially in the past five years. Approaches related to battery performance prognostics are categorized into physics-based, data-driven and hybrid classes. Selection of the battery PHM approach requires to take the user requirement, data availability and degradation mechanisms attainability into consideration. Based on the survey, we also proposed research and development perspectives to conduct further studies on the battery PHM, including the approach selection, health management, performance evaluation, uncertainty treatment, application economics, as well as environmental issues. We focused on PHM of lithium-ion batteries, given the fact that several publications discussed other types of batteries (e.g., lead-acid batteries).

A review on prognostics and health management (PHM) methods of lithium-ion batteries

/pdf/merging-data-sources-to-predict-remaining-useful-life-an-2j6tjvybey.pdf

Merging Data Sources to Predict Remaining Useful Life – An Automated Method to Identify Prognostic Parameters

The Joint Strike Fighter (JSF) program is the focal point for defining the next generation of strike aircraft weapon systems for the Navy, Marines, Air Force, and allies. The focus of the program is affordability reducing the costs of development, production, and ownership of the JSF family of aircraft. In addition to affordability as a "pillar" of the JSF program, three additional pillars have been established: survivability, lethality, and supportability/deployability. These four pillars have established the foundation for the design and development of the JSF weapon system. One of the keys to providing an affordable approach to supportability and deployability lies in the strategy of prognostics and health management (PHM) and how it supports the concept of autonomic logistics. This paper focuses on the contribution of PHM and its relationship to autonomic logistics.

G. Smith

Papers

Development of a prognostics and health management capability for the Joint Strike Fighter