Sijia Wang

Recently, transfer learning (TL) approaches have been extensively applied in industrial cross-domain fault diagnosis, most of which depend on the consistency assumption of the source and target fault categories. In practice, it is common to utilize multiple source domains for transfer learning, but each of them may not include all fault categories in the target domain, which are referred to as incomplete multisource domains. For the challenge of fault diagnosis under incomplete multisource domains, a cross-domain bilateral transfer learning (CDBTL) method is proposed in this article. First, a cross-domain bilateral transfer strategy is developed, where the source and target domains are reconstructed from each other and their distribution differences are reduced by minimizing the reconstruction error to avoid negative transfer. Then, for the source domain with label information, CDBTL maximizes the between-class distance of different fault categories and minimizes the within-class distance of the same fault category to ensure the discriminative nature of its feature representation. Afterwards, the common projection matrix is learned through the mutual cooperation of projection matrices between different incomplete source domains and target domain to compensate for the missing fault categories in a single source domain. The key to discriminate CDBTL from many exiting TL algorithms is that it relaxes the restriction of consistent fault categories in the source and target domains, and skillfully integrates the knowledge of multiple incomplete source domains. Extensive experiments on Tennessee Eastman process demonstrate the superiority of CDBTL in solving cross-domain fault diagnosis problem, whose accuracy is averagely improved by 17.99% compared with eleven existing algorithms. Note to Practitioners —The changing industrial operating modes (domains) may result in different data distributions and fault categories between the historical mode (source domain) and current mode (target domain). Traditional machine learning methods usually fail to diagnose under the above domain and category inconsistencies. The key work in this article is to develop a cross-domain bilateral transfer learning (CDBTL) algorithm to realize cross-domain fault diagnosis under incomplete multisource domains. The proposed algorithm can avoid negative transfer while reducing inter-domain differences, and utilize the mutual cooperation of multiple source domains to fully cover the fault categories in the target domain. The constructed CDBTL model can be combined with various classifiers, and the learned classifiers can be directly applied to fault diagnosis in advanced manufacturing industry under incomplete multisource domains.

The performance of traditional multivariate statistical process monitoring (MSPM) approaches highly depends on data quality. Due to noise disturbance, sensor drift, and some circumstance factors, process data are inevitably contaminated with uncertainty, which may destroy the correlation structure of original process data, resulting in an increase in false alarms and missed detections of traditional methods. In such cases, it is urgent to explore a new form to scientifically describe uncertainty and establish a reliable fault detection model. Inspired by the demands, a generalized Gaussian distribution-based interval principal component analysis (GGD-IPCA) method is proposed for industrial processes with uncertainty. First, a GGD-based interval estimation method is developed to transform uncertainty-contaminated data into interval-valued data and represent process uncertainty in a generalized distribution form. Then, a new interval feature extraction algorithm called GGD-IPCA is proposed by redefining mean, inner product, and square norm operators under an adjustable interval distribution form of process uncertainty with different shape parameters. Two monitoring statistics applicable to interval data are defined to monitor the operating conditions. The key to discriminate GGD-IPCA from many well-established IPCA methods, including centers PCA and complete-information PCA (CIPCA), is its ability to flexibly reduce the dimension of interval data with full consideration of various interval distributions. Experiments show that compared with the other eight algorithms, GGD-IPCA averagely reduces MDR by 4.35% with FAR no more than 2.00% in a numerical example and reduces FAR by 15.60% with average MDR as low as 2.94% in the Tennessee Eastman (TE) process.

The fault detection capability of traditional data-driven process monitoring methods is highly dependent on the quality of process data. However, affected by measurement noise, harsh operation scenarios and other factors, the process data are inevitably contaminated by uncertainty in real processes. In this article, a vertices packaging-based interval independent component analysis (VP-I ² CA) method is proposed to monitor the uncertain non-Gaussian processes. First, a variable bandwidth-kernel density estimation-based measurement error estimation method is developed to describe the uncertainty-contaminated process data in interval form using limited reliable data samples. Then, VP-I ² CA is developed to estimate the demixing matrix based on hypermatrices constructed by vertices encoding, which includes all possible combinations between the bounds of interval data by explicitly considering the existence of uncertainty. In order to reduce computational complexity, the idea of data packaging is introduced to represent the hyper-independent components in interval form with a series of values by packaging all possible feature information hidden in uncertain process data. Afterwards, four monitoring statistics are constructed to monitor the systematic and nonsystematic parts of process operation variation. The proposed algorithm is verified in both a six-variable numerical simulation system and a continuous stirred tank reactor system.