The problem of fault classification in industry has been studied extensively. Most classification algorithms are modeled on the premise of data balance. However, the difficulty of collecting industrial data in different modes is quite different. This inevitably leads to data imbalance, which will adversely affect the fault classification performance. This article proposes a novel data augmentation classifier (DAC) for imbalanced fault classification. Data augmentation based on generative adversarial networks (GANs) is an effective way to solve the problem of unbalanced classification. However, the randomness of the GAN generation process restricts the effect of data enhancement. DAC proposes a data selection strategy based on data filtering and data purification in model training to solve this problem. In addition, DAC combines supervised learning and data generation processes to obtain an end-to-end model. Meanwhile, multigenerator structure of DAC (MDAC) is proposed to solve the problem of incomplete learning of a single generator when data imbalances get complicated. The proposed DAC and MDAC are applied in two fault classification cases of the Tennessee Eastman (TE) benchmark process, results of which show superiority of DAC and MDAC compared to existing methods.

In the era of industrial big data, data-driven soft-sensor models have become an important method to guide production and optimize control. However, due to the limitation of data acquisition methods, the industrial data obtained in practice have unavoidable defects that affect the performance of soft sensors. Aiming at the unbalanced sampling, inaccurate matching, and partial missing of industrial process data, this article proposes an augmented multidimensional convolutional neural network (CNN) for industrial soft sensing. For complete process data information, we stitch the fine-grained data to obtain coarse-grained data and then use a CNN to extract deep features. On the basis of analyzing the physical meaning of data, the structure of multidimensional convolution is designed to focus on different details of process information. In this framework, the problem of partial missing data is emphasized. Then, mix-grained data augmentation strategies are invented to solve this problem and improve the performance of multidimensional CNN (MDCNN) soft sensors. The proposed augmented MDCNN is applied to the f-CaO prediction of the cement clinker production process, results of which show superiority compared to existing methods.

Just-in-time learning (JITL) is a widely used method for online soft sensing. The limitation of available data and the increase of sample dimensions will make the historical dataset sparse, seriously impair the reliability and usability of JITL applications in the industry. To this end, data augmentation technology (DA) is introduced into the JITL framework for the first time to improve the performance of JITL-based soft sensors. In this article, a novel causality-informed variational autoencoder (CIVAE) is developed to generate virtual samples to augment the historical dataset. Based on this, a complete framework of data augmentation just-in-time learning (DA-JITL) is formulated offline and online and implemented with two different strategies. Finally, a numeral example and an actual industrial example are applied to verify the effectiveness of the proposed method. Besides, the effect of virtual data on JITL and the influence of virtual data volume, virtual data ratio and other factors are carefully discussed on the proposed method. In the industrial case, two indicators (rmse and R2) of the proposed method have been improved by an average of 25% and 17%, respectively, compared to the traditional JITL approach.

The content of free calcium oxide (f-CaO) in clinker significantly determines the quality of the final cement production. However, in practice, the value of f-CaO content in clinker is off-line sampled manually with a significant time interval and then analyzed in a laboratory with a large time delay, which could meet the needs for monitoring and control of cement quality. To tackle this problem, this article proposes a data-driven model based on deep dynamic features extracting and transferring methods to build a virtual sensor for f-CaO content prediction. First, in this model, large-scale unlabeled data collected from the process distributed control system (DCS) take a vital effect in extracting nonlinear dynamic features along with the limited labeled data samples. Then, the extracted features are transferred to a powerful regression model, the eXtreme Gradient Boosting (XGBoost), for output f-CaO prediction. Besides, an incremental model updating strategy is proposed for the augment of online data samples, which facilitates the virtual sensor to adapt the process time-variant characteristics. Finally, the proposed virtual sensor is verified by a data set acquired from a real cement production process. Comparing with traditional statistical modeling methods, the prediction accuracy of f-CaO content is significantly improved.

In the field of intelligent manufacturing and industrial big data, data-driven Industrial Intelligence Models (IIMs) based on machine learning have become indispensable for modern industrial systems. While IIMs are renowned for their effective learning capabilities, a critical challenge persists: Their performance is severely compromised by the substantial quality gap between raw industrial data and model-ready data. To address this core issue, Industrial Data Augmentation (IDA) has emerged as a transformative solution, yet existing research lacks systematic frameworks and implementation guidelines. This paper presents the first comprehensive survey establishing IDA as an independent research domain. We propose a novel taxonomy categorizing IDA methods by transformation-based, interpolation-based, and distribution estimation-based approaches. Beyond methodology analysis, we conduct a systematic review of frontier IDA applications spanning key performance indicator prediction, anomaly monitoring, fault diagnosis, and defect detection. Significantly, an open-source IDA toolbox implementing twenty IDA algorithms is introduced to facilitate ongoing development and application, available at https://github.com/3uchen/IdaLy. Finally, this paper highlights current challenges and future prospects for the IDA, seeking to motivate and steer further research in this area.

For fault classification in industrial processes, both inaccurate and incomplete supervised information commonly exist in practice, which raise a big challenge to the research field. In this article, a weakly supervised form of the multilayer perceptron (MLP) model is proposed, with considerations of both inaccurate and incomplete labels in fault classification. First, a label probability transition matrix is used to describe the relationship between the inaccurate labels and unknown true labels of process data. This transition matrix is estimated through a Gaussian mixture model, and then used to correct the loss function of the MLP model. Based on the framework of the developed weakly supervised MLP (WS-MLP) model, the information of incomplete labels in the training data set is incorporated simultaneously with the inaccurate label information. The performance of the proposed model WS-MLP is evaluated through two industrial benchmark data sets, results of which indicate its effectiveness under different application cases.