In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.

For prognostics and health management (PHM) of mechanical systems, a core task is to predict machine remaining useful life (RUL). Currently, deep structures with automatic feature learning, such as long short-term memory (LSTM), have achieved great performances for RUL prediction. However, the conventional LSTM network only uses the learned features at last time step for regression or classification, which is not efficient. Besides, some handcrafted features with domain knowledge may convey additional information for the prediction of RUL. It is thus highly motivated to integrate both those handcrafted features and automatically learned features for RUL prediction. In this paper, we propose an attention based deep learning framework for machine RUL prediction. The LSTM network is employed to learn sequential features from raw sensory data. Meanwhile, the proposed attention mechanism is able to learn the importance of features and time steps, and assign larger weights to more important ones. Moreover, a feature fusion framework is developed to combine the handcrafted features with automatically learned features to boost the performance of RUL prediction. Extensive experiments have been conducted on two real datasets and experimental results demonstrate that our proposed approach outperforms the state-of-the-arts.

One key issue in text mining and natural language processing (NLP) is how to effectively represent documents using numerical vectors. One classical model is the Bag-of-Words (BoW). In a BoW-based vector representation of a document, each element denotes the normalized number of occurrence of a basis term in the document. To count the number of occurrence of a basis term, BoW conducts exact word matching, which can be regarded as a hard mapping from words to the basis term. BoW representation suffers from its intrinsic extreme sparsity, high dimensionality, and inability to capture high-level semantic meanings behind text data. To address the above issues, we propose a new document representation method named Fuzzy Bag-of-Words (FBoW) in this paper. FBoW adopts a fuzzy mapping based on semantic correlation among words quantified by cosine similarity measures between word embeddings. Since word semantic matching instead of exact word string matching is used, the FBoW could encode more semantics into the numerical representation. In addition, we propose to use word clusters instead of individual words as basis terms and develop Fuzzy Bag-of-WordClusters (FBoWC) models. Three variants under the framework of FBoWC are proposed based on three different similarity measures between word clusters and words, which are named as FBoWCmean, FBoWCmax and FBoWCmin, respectively. Document representations learned by the proposed FBoW and FBoWC are dense and able to encode high-level semantics. The task of document categorization is used to evaluate the performance of learned representation by the proposed FBoW and FBoWC methods. The results on seven real word document classification datasets in comparison with six document representation learning methods have shown that our methods FBoW and FBoWC achieve the highest classification accuracies.

Condition monitoring and fault diagnosis are of significance to improve the safety and reliability of motors, given their widespread applications in virtually every branch of the industry. Sequential data modeling based on recurrent neural network (RNN) and its variants have drawn increasing attention because the temporal nature of motor signals can be well leveraged for motor analysis. One common drawback of prior research is that signals measured on motors are typically analyzed with a fixed time window, making it difficult to trade off between global state estimation and local feature extraction. This paper presents a deep learning-based model termed Multi-Resolution & multi-Sensor Fusion Network (MRSFN) for motor fault diagnosis, through multi-scale analysis of motor vibration and stator current signals. Specifically, vibration and current signals are first segmented by analysis windows of varying lengths to create a new data stream for the joint representation and temporal encoding of the original sensor signals, based on two network structures: convolutional neural network (CNN) and long short-term memory (LSTM). The advantage of the developed method is that it automatically learns the discriminative features through the network training process, without requiring manual feature selection as is typically the case in prior methods. By considering the temporal dependence of the signals being analyzed, the developed multi-resolution fusion technique not only improves the effectiveness of feature extraction but is also adaptive to varying motor speed. Two case studies demonstrate the advantages of the developed method.

Buildings consume quite a lot of energy; hence, the issue of building energy efficiency has attracted a great deal of attention in recent years. A key factor in achieving this objective is occupancy information that directly impacts on energy-related building control systems. In this paper, we leverage on environmental sensors that are nonintrusive and cost-effective for building occupancy estimation. Our result relies on feature engineering and learning. The conventional feature engineering requires one to manually extract relevant features without a clear guideline. This blind feature extraction is labor intensive and may miss some significant implicit features. To address this issue, we propose a convolutional deep bidirectional long short-term memory (CDBLSTM) approach that contains a convolutional network and a deep structure to automatically learn significant features from the sensory data without human intervention. Moreover, the long short-term memory networks are able to capture temporal dependencies in the data and the bidirectional structure can take the past and future contexts into consideration for the final identification of occupancy. We have conducted real experiments to evaluate the performance of our proposed CDBLSTM approach. Instead of estimating the exact number of occupants, we attempt to identify the range of occupants, i.e., zero, low, medium, and high, which is adequate for most of building control systems. The experimental results indicate the effectiveness of our proposed approach compared with the state-of-the-art methods.

Machine learning, especially deep learning, has been extensively applied and studied in the area of machine health monitoring. For machine health monitoring systems (MHMS), major efforts have been put into designing and deploying more and more complex machine learning models. Those black-box models are nontransparent toward their working mechanism. However, this research trend brings huge potential risks in real life. Since machine health monitoring itself belongs to high stake decision applications, the outputs of the autonomous monitoring systems should be trustworthy and reliable, which refers to obtain explainability. Then, it comes to the following key question: why the deployed MHMS predicts what they predict. In this article, we shed some light on this meaningful research direction: explainable MHMSs (EMHMS). In EMHMS, the machine doctor could act like a real doctor who can not only make a diagnosis but also describe the patient's symptoms. First, we propose a specific convolutional neural network (CNN) structure, named DecouplEd Feature-Temporal CNN (DEFT-CNN), to balance precision-explainability tradeoff. Specifically, feature information and temporal information have been encoded in different stages of our model. The spatial attention module is added to boost the performance of the model. Then, to explain the decision of the model, we adopt gradient-based methods to generate features and temporal saliency maps highlighting which kinds of features and time steps are keys for the model's predictions. Finally, we conduct the experimental studies on two real datasets to verify the effectiveness of our proposed framework.