The main roles of fault detection and diagnosis (FDD) for industrial processes are to make an effective indicator which can identify faulty status of a process and then to take a proper action against a future failure or unfavorable accidents. In order to enhance many process performances (e.g., quality and throughput), FDD has attracted great attention from various industrial sectors. Many traditional FDD techniques have been developed for checking the existence of a trend or pattern in the process or whether a certain process variable behaves normally or not. However, they might fail to produce several hidden characteristics of the process or fail to discover the faults in processes due to underlying process dynamics. In this paper, we present current research and developments of FDD approaches for process monitoring as well as a broad literature review of many useful FDD approaches.

Fault detection and classification (FDC) is important for semiconductor manufacturing to monitor equipment's condition and examine the potential cause of the fault. Each equipment in the semiconductor manufacturing process is often accompanied by a large amount of sensor readings, also called status variable identification (SVID). Identifying the key SVIDs accurately can make it easier for engineers to monitor the process and maintain the stability of the process and wafer productive yields. This article proposes using the random forests algorithm to analyze the importance of SVIDs of equipment sensors, automatically filters the key SVID by using k-means, and integrates various machine learning methods to verify the key SVIDs and identify key processing time and steps. Upon the key parameters are identified, the key processing time and steps are investigated subsequently. The ensemble models constructed on k-nearest neighbors (kNNs) and naïve Bayes classifiers are presented for classifying wafers as normal or abnormal. Data visualization of multidimensional key SVIDs is performed by using t-distributed stochastic neighbor embedding (t-SNE) to create a graphical aid in FDC for the process engineer. An empirical study is conducted to validate the proposed data-driven framework for fault detection and diagnostic. The experimental results demonstrate that the proposed framework can detect abnormality effectively with highly imbalanced classes and also gain insightful information about the key SVIDs and corresponding key processing time and steps.

Predictive maintenance (PdM) is useful for engineers to schedule maintenance flexibly, to operate equipment efficiently, and also to avoid unexpected downtime. Remaining useful life (RUL) prediction is critical for PdM before the need for component replacement. Data-driven approaches have attracted more attention for RUL prediction in flexible production. Compared with statistical-based and conventional machine learning approaches, deep learning-based approaches can extract critical features from raw equipment sensor data without prior knowledge from a domain expert. This study proposes a temporal convolution-based long-short term memory (TCLSTM) network with attention mechanism to extract features from equipment sensor data and to build a regression model for RUL prediction. Temporal convolutional networks (TCN) are used for feature extraction. LSTM and attention layers are used to learn temporal dependencies among the extracted features. The fully connected network consists of dense layers and is used to build the RUL prediction model. To evaluate the effectiveness of the proposed method, an empirical dataset from a semiconductor ion mill etching process was used. According to the comparison results, the proposed TCLSTM network with attention mechanism has the lowest prediction error and outperforms TCN, LSTM, and other machine learning approaches. The experimental results demonstrate the practical viability of the proposed approach.

With the development of smart manufacturing, in order to detect abnormal conditions of the equipment, a large number of sensors have been used to record the variables associated with production equipment. This study focuses on the prediction of Remaining Useful Life (RUL). RUL prediction is part of predictive maintenance, which uses the development trend of the machine to predict when the machine will malfunction. High accuracy of RUL prediction not only reduces the consumption of manpower and materials, but also reduces the need for future maintenance. This study focuses on detecting faults as early as possible, before the machine needs to be replaced or repaired, to ensure the reliability of the system. It is difficult to extract meaningful features from sensor data directly. This study proposes a model based on an Autoencoder Gated Recurrent Unit (AE-GRU), in which the Autoencoder (AE) extracts the important features from the raw data and the Gated Recurrent Unit (GRU) selects the information from the sequences to forecast RUL. To evaluate the performance of the proposed AE-GRU model, an aircraft turbofan engine degradation simulation dataset provided by NASA was used and a comparison made of different recurrent neural networks. The results demonstrate that the AE-GRU is better than other recurrent neural networks, such as Long Short-Term Memory (LSTM) and GRU.