Remaining useful life (RUL) prediction of rolling element bearings plays a pivotal role in reducing costly unplanned maintenance and increasing the reliability, availability, and safety of machines. This paper proposes a hybrid prognostics approach for RUL prediction of rolling element bearings. First, degradation data of bearings are sparsely represented using relevance vector machine regressions with different kernel parameters. Then, exponential degradation models coupled with the Frechet distance are employed to estimate the RUL adaptively. The proposed approach is evaluated using the vibration data from accelerated degradation tests of rolling element bearings and the public PRONOSTIA bearing datasets. Experimental results demonstrate the effectiveness of the proposed approach in improving the accuracy and convergence of RUL prediction of rolling element bearings.

A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings

With the rapid development of smart manufacturing, data-driven fault diagnosis has attracted increasing attentions. As one of the most popular methods applied in fault diagnosis, deep learning (DL) has achieved remarkable results. However, due to the fact that the volume of labeled samples is small in fault diagnosis, the depths of DL models for fault diagnosis are shallow compared with convolutional neural network in other areas (including ImageNet), which limits their final prediction accuracies. In this research, a new TCNN(ResNet-50) with the depth of 51 convolutional layers is proposed for fault diagnosis. By combining with transfer learning, TCNN(ResNet-50) applies ResNet-50 trained on ImageNet as feature extractor for fault diagnosis. Firstly, a signal-to-image method is developed to convert time-domain fault signals to RGB images format as the input datatype of ResNet-50. Then, a new structure of TCNN(ResNet-50) is proposed. Finally, the proposed TCNN(ResNet-50) has been tested on three datasets, including bearing damage dataset provided by KAT datacenter, motor bearing dataset provided by Case Western Reserve University (CWRU) and self-priming centrifugal pump dataset. It achieved state-of-the-art results. The prediction accuracies of TCNN(ResNet-50) are as high as 98.95% ± 0.0074, 99.99% ± 0 and 99.20% ± 0, which demonstrates that TCNN(ResNet-50) outperforms other DL models and traditional methods.

A transfer convolutional neural network for fault diagnosis based on ResNet-50

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

Fault diagnosis and prognosis are some of the most crucial functionalities in complex and safety-critical engineering systems, and particularly fault diagnosis, has been a subject of intensive research in the past four decades. Such capabilities allow for detection and isolation of early developing faults as well as prediction of fault propagation, which can allow for preventive maintenance, or even serve as a countermeasure to the possibility of catastrophic incidence as a result of a failure. Following a short preliminary overview and definitions, this article provides a survey of recent research on fault prognosis. Additionally, we report on some of the significant application domains where prognosis techniques are employed. Finally, some potential directions for future research are outlined.

Failure Prognosis and Applications—A Survey of Recent Literature

The degradation of bearings plays a key role in the failures of industrial machinery Prognosis of bearings is critical in adopting an optimal maintenance strategy to reduce the overall cost and to avoid unwanted downtime or even casualties by estimating the remaining useful life (RUL) of the bearings Traditional data-driven approaches of RUL prediction rely heavily on manual feature extraction and selection using human expertise This paper presents an innovative two-stage automated approach to estimate the RUL of bearings using deep neural networks (DNNs) A denoising autoencoder-based DNN is used to classify the acquired signals of the monitored bearings into different degradation stages Representative features are extracted directly from the raw signal by training the DNN Then, regression models based on shallow neural networks are constructed for each health stage The final RUL result is obtained by smoothing the regression results from different models The proposed approach has achieved satisfactory prediction performance for a real bearing degradation dataset with different working conditions

A Two-Stage Approach for the Remaining Useful Life Prediction of Bearings Using Deep Neural Networks

Prognostics and health management allows us to predict the remaining useful life (RUL) of machinery, which is important in reducing maintenance costs and downtime, and even preventing casualties. Bearing faults account for a large proportion of machine faults. To predict the RUL of bearings, health indicators that represent the degeneration state are extracted based on the Hilbert–Huang transform and selected according to Spearman's coefficient. A model-based particle filter method is then used to track the degradation state. The unknown parameters in the nonlinear system are updated by a new method of logarithmic linear recursive least squares. A recursive maximum likelihood estimation algorithm is introduced to learn the noise in the system, and an innovative parameter fusion technique based on normalized partial derivative weights is used. Finally, the RUL of the bearings is predicted. The proposed method is validated using data from the test platform PRONOSTIA.

Prognostics and Health Management of Bearings Based on Logarithmic Linear Recursive Least-Squares and Recursive Maximum Likelihood Estimation

Blackboard Mechanism Based Ant Colony Theory for Dynamic Deployment of Mobile Sensor Networks

The gateway realizes the fusion of wireless sensor network and external network. Some low performance gateways cannot meet the requirement of surge data collection. Consequently, a gateway that based on PXA270, using embedded Linux is designed to meet the requirement. To protect the data that transmitted by Ethernet through the gateway, a TCP/IP strategy is constituted, which can reduce the probability of data missing. To realize the communication of WSN and external network, the application layer program is designed. It can collect, process, transmit the data of WSN, and supply multi-clients services including data display or download concurrently. The client can visit the gateway via Website or command console.

The Design and Realization of Embedded Gateway Based on WSN

Time synchronization is a critical middleware service of distributed system. In particular, wireless sensor networks is a distributed system which makes extensive use of synchronized time in many contexts (e.g. for data fusion, TDMA schedules, synchronized sleep periods, etc.). In addition, synchronization precision has become a critical area of research today. Time synchronization with very high precision is needed at some special application. In this paper, we proposed a high degree of accuracy time synchronization Protocol--Physical Layer Integrated Synchronization Protocol (PLISP). Different from adding timestamp in MAC layer of traditional time synchronization protocol, we advocate a novel way to add timestamp. We add timestamp in physical layer which can utmost reduce influence of nondeterminacy factor to synchronization precision. We get time synchronization precision is less than 1 µs in experiments. Result shows that this method is feasible and can be used to wireless sensor networks.

Highly precise time Synchronization Protocol for ZigBee networks

To improve the quality of service (QoS) in sensing coverage, wireless sensor networks (WSN) composed of immobile nodes and mobile nodes should optimize the distribution of mobile nodes after their random deployment. According to the pre-research work we know that the node density is closely relevant to QoS in sensing coverage when the nodes are randomly deployed in the target region. In this paper the target region is divided into different parts being not overlapped with the others, a modified particle swarm optimization (PSO) is proposed to optimize the node density of different parts according to the expectation of QoS in the parts and the virtual force between the nodes is proposed to adjust the position of mobile nodes. It is suggested by the simulated experiment results that the method proposed to optimize the mobile nodes in this paper can improve the QoS in sensing coverage.

Ping Song

Papers

Prognostics and Health Management of Bearings Based on Logarithmic Linear Recursive Least-Squares and Recursive Maximum Likelihood Estimation

Blackboard Mechanism Based Ant Colony Theory for Dynamic Deployment of Mobile Sensor Networks

The Design and Realization of Embedded Gateway Based on WSN

Highly precise time Synchronization Protocol for ZigBee networks

Researching on Optimal Distribution of Mobile Nodes in Wireless Sensor Networks being Deployed Randomly