Deep learning and its applications to machine health monitoring

Artificial intelligence for fault diagnosis of rotating machinery: A review

Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.

A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method

Applications of machine learning to machine fault diagnosis: A review and roadmap

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

Machinery condition monitoring has entered the era of big data and some research has been done based on big data. Abnormal segments, such as missing segments and drift segments, are inevitable in big data acquired from harsh industrial environment due to temporary sensor failures, network segment transmission delays, or accidental loss of some collected data and so on. Being independent of the machinery condition, the abnormal segments not only reduce the quality of the data for condition monitoring and big data analysis, but also bring a heavy computation load. However, there are few reports to address abnormal segment detection for further data cleaning in the field of machinery condition monitoring. Therefore, an abnormal segment detection method is proposed to improve the quality of big data. First, a sliding window is used to separate the data into different segments. Then, 14 kinds of time-domain features are extracted from each segment and principle component analysis (PCA) is employed to extract the principle components from these features. In addition, local outlier factor (LOF) is calculated based on the principle components to evaluate the degree of being an outlier for each segment. Finally, the data, including a drift segment from a real wind turbine, are used to verify the effectiveness of the proposed method.

A LOF-Based Method for Abnormal Segment Detection in Machinery Condition Monitoring

Condition monitoring of machinery has entered the big data era, while the existence of dirty data reduces the quality of the whole data. In order to recognize the dirty data included in machinery monitoring data, a new method is proposed in this paper. First, a feature named sampled power index (SPI) is designed to transform the dirty data recognition issue into the outlier recognition. Then the windowing technique, the difference operation and the logarithm transform are introduced to reduce the feature tendency and the feature volatility. Next, auto regression-generalized autoregressive conditional heteroskedasticity (AR-GARCH) model is applied to regress the feature series and produce the crippled local means and local volatilities. Finally, the features are normalized and the 3σ criterion is applied to recognize the dirty data. The performance and the feasibility of this proposed method are evaluated by a simulation and an experiment. The results validate the effectiveness of the proposed method.

Xin Zhou

Papers

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

A LOF-Based Method for Abnormal Segment Detection in Machinery Condition Monitoring

A dirty data recognition method for machinery condition monitoring in big data era

Response Characteristics of Gas Concentration Level in Mining Process and Intelligent Recognition Method Based on BI-LSTM