A Deep Belief Network-based Fault Detection Method for Nonlinear Processes

Sensor fault detection of wind turbines plays an important role in improving the reliability and stable operation of turbines. The supervisory control and data acquisition (SCADA) system of a wind turbine provides promising insights into sensor fault detection due to the accessibility of the data and the abundance of sensor information. However, SCADA data are essentially multivariate time series with inherent spatio-temporal correlation characteristics, which has not been well considered in the existing wind turbine fault detection research. This paper proposes a novel classification-based fault detection method for wind turbine sensors. To better capture the spatio-temporal characteristics hidden in SCADA data, a multiscale spatio-temporal convolutional deep belief network (MSTCDBN) was developed to perform feature learning and classification to fulfill the sensor fault detection. A major superiority of the proposed method is that it can not only learn the spatial correlation information between several different variables but also capture the temporal characteristics of each variable. Furthermore, this method with multiscale learning capability can excavate interactive characteristics between variables at different scales of filters. A generic wind turbine benchmark model was used to evaluate the proposed approach. The comparative results demonstrate that the proposed method can significantly enhance the fault detection performance.

Download Full-text

Fault Detection Prediction Using a Deep Belief Network-Based Multi-Classifier in the Semiconductor Manufacturing Process

International Journal of Software Engineering and Knowledge Engineering ◽

10.1142/s0218194019400126 ◽

2019 ◽

Vol 29 (08) ◽

pp. 1125-1139

Author(s):

Jae Kwon Kim ◽

Jong Sik Lee ◽

Young Shin Han

Keyword(s):

Fault Detection ◽

Manufacturing Process ◽

Semiconductor Manufacturing ◽

High Performance ◽

Semiconductor Industry ◽

Deep Belief Network ◽

Second Phase ◽

Data Sets ◽

Belief Network ◽

Imbalance Problem

The semiconductor manufacturing process is very complex, and it is the most important part of the semiconductor industry. In order to test whether or not wafers are functioning normally, a pass/fail test is conducted; however, time and cost needed for this testing increase as the number of chips increases. To address this, a machine learning technique is adopted and a high-performance classifier is needed to determine whether a pass/fail test is accurate or not. In this paper, a deep belief network (DBN)-based multi-classifier is proposed for fault detection prediction in the semiconductor manufacturing process. The proposed method consists of two phases: The first phase is a data pre-processing phase in which features required for semiconductor data sets are extracted and the imbalance problem is solved. The second phase is to configure the multi-DBN using selected features. A DBN classifier is created for each feature and, finally, fault detection prediction is performed. The proposed method showed excellent performance and can be used in the semiconductor manufacturing process efficiently.

Download Full-text