Search

Research studies on data-driven approaches to rotating components and rolling element bearing (REB) prognostics have recently witnessed a rapid increase. These data-driven methods rely on sensor data for condition monitoring and degradation assessments; however, the problem of mining features from these sophisticated data using appropriate intelligent methods and choosing a practically reliable predictive model(s) has become a global concern. Vibration monitoring for REBs have over the years shown great effectiveness. Although monotonic statistical features serve as reliable health indicators (HIs), relying on a single feature for optimal bearing degradation assessment is inefficient. By fusing highly monotonic features using appropriate methods, a more reliable HI can be constructed and from this, various degradation states/stages and time to start prediction (TSP) can be identified by mapping known failure modes/degradation states to cluster points from clustering algorithms. Emphatically, the choice of regression algorithms for prognostics poses more concern as engineers and data scientists are faced with choosing between Bayessian machine learning (ML) and deep learning (DL) methods. This study presents a methodology for constructing a reliable HI for bearing prognostics, choosing a reliable TSP, and provides a comparison between ML and DL methods for bearing prognostics. As representatives of both domains, the Gaussian process regression (GPR) and the deep belief network (DBN) are introduced and compared. The results provide a reliable paradigm for prognosible feature representation for REBs and for choosing between both domains while considering their dependencies, efficiencies, and deficiencies.

The emergence of prognostics and health management as a condition-based maintenance approach has greatly improved productivity, maintainability, and most essentially, reliability of systems. Invariably, a rolling-element bearing (REB) is the heart of rotating components; however, its failure can have daunting effects ranging from costly unexpected breakdown to catastrophic life-threatening situations. Consequently, the need for accurate condition monitoring and prognostics of REBs cannot be overemphasized. In view of achieving a more comprehensive condition assessment for prognostics of REBs, this study proposes a kernel principal component analysis (KPCA) feature fusion technique for degradation assessment and a deep learning model for prognostics. The deep learning method-deep long short-term memory (DLSTM) has shown an evident comparative advantage over the basic LSTM model and standard recurrent neural networks for time-series forecasting. Subsequently, the proposed prognostics model-KPCA-DLSTM performance was validated with a run-to-failure experiment on REBs and evaluated for accuracy against other prognostics methods reported in other works of literature using standard performance metrics. The proposed method was also used for REB remaining useful life (RUL) prediction and the results show that the KPCA-DLSTM does not only reflect a more monotonic bearing degradation trend but also yields better prognostics results.

This paper develops a data-driven remaining useful life prediction model for solenoid pumps. The model extracts high-level features using stacked autoencoders from decomposed pressure signals (using complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm). These high-level features are then received by a recurrent neural network-gated recurrent units (GRUs) for the RUL estimation. The case study presented demonstrates the robustness of the proposed RUL estimation model with extensive empirical validations. Results support the validity of using the CEEMDAN for non-stationary signal decomposition and the accuracy, ease-of-use, and superiority of the proposed DL-based model for solenoid pump failure prognostics.

Sensor acquired signal has been a fundamental measure in rotary machinery condition monitoring (CM) to enhance system reliability and stability. Inappropriate sensor mounting can lead to loss of fault-related information and generate false alarms in industrial systems. To ensure reliable system operation, in this paper we investigate a system’s multiple degrees-of-freedom (DOF) using the finite element method (FEM) to find the optimum sensor mounting position. An appropriate sensor position is obtained by the highest degree of deformation in FEM modal analysis. The effectiveness of the proper sensor mounting position was compared with two other sensor mounting points, which were selected arbitrarily. To validate the effectiveness of this method we considered a gear-actuator test bench, where the sensors were mounted in the same place as the FEM simulation. Vibration data were acquired through these sensors for different health states of the system and failure patterns were recognized using an artificial neural network (ANN) model. An ANN model shows that the optimum sensor mounting point found in FEM has the highest accuracy, compared to other mounting points. A hybrid CM framework, combining the physics-based and data-driven approaches, provides robust fault detection and identification analysis of the gear-actuator system.

This paper develops a novel hybrid feature learner and classifier for vibration-based fault detection and isolation (FDI) of industrial apartments. The trained model extracts high-level discriminative features from vibration signals and predicts equipment state. Against the limitations of traditional machine learning (ML)-based classifiers, the convolutional neural network (CNN) and deep neural network (DNN) are not only superior for real-time applications, but they also come with other benefits including ease-of-use, automated feature learning, and higher predictive accuracies. This study proposes a hybrid DNN and one-dimensional CNN diagnostics model (D-dCNN) which automatically extracts high-level discriminative features from vibration signals for FDI. Via Softmax averaging at the output layer, the model mitigates the limitations of the standalone classifiers. A diagnostic case study demonstrates the efficiency of the model with a significant accuracy of 92% (F1 score) and extensive comparative empirical validations.

An effective remaining useful life (RUL) estimation method is of great concern in industrial machinery to ensure system reliability and reduce the risk of unexpected failures. Anticipation of an electric motor’s future state can improve the yield of a system and warrant the reuse of the industrial asset. In this paper, we present an effective RUL estimation framework of brushless DC (BLDC) motor using third harmonic analysis and output apparent power monitoring. In this work, the mechanical output of the BLDC motor is monitored through a coupled generator. To emphasize the total power generation, we have analyzed the trend of apparent power, which preserves the characteristics of real power and reactive power in an AC power system. A normalized modal current (NMC) is used to extract the current features from the BLDC motor. Fault characteristics of motor current and generator power are fused using a Kalman filter to estimate the RUL. Degradation patterns for the BLDC motor have been monitored for three different scenarios and for future predictions, an attention layer optimized bidirectional long short-term memory (ABLSTM) neural network model is trained. ABLSTM model’s performance is evaluated based on several metrics and compared with other state-of-the-art deep learning models.