In this paper, a challenging fault diagnosis task is studied, in which no samples of the target faults are available for the model training. This scenario has hardly been studied in industrial research. But it is a common problem that massive fault samples are not available for the target faults, which limits the successes of conventional data-driven approaches in practical application. Here, we introduce the idea of zero-shot learning into the industry field, and tackle the zero-sample fault diagnosis task by proposing the fault description based attribute transfer method.

Fault diagnosis, which identifies the root cause of the observed out-of-control status, is essential to the counteraction or elimination of faults in industrial processes. Many conventional data driven fault diagnosis methods ignore the fault tendency of abnormal samples, and need a complete retraining process to include the newly collected abnormal samples or fault classes. In this study, a broad convolutional neural network (BCNN) is designed with incremental learning capability for solving the aforementioned issues. The proposed method combines several consecutive samples as a data matrix, and then extracts both fault tendency and nonlinear structure from the obtained data matrix using convolutional operation. After that, weights in fully connected layer can be trained based on the obtained features and their corresponding fault labels. Because of the architecture of this network, the diagnosis performance of BCNN model can be improved by adding newly generated additional features. Finally, the incremental learning capability of the proposed method is also designed, so that BCNN model can update itself to include new coming abnormal samples and fault classes. Experimental results illustrate that it can better capture the characteristics of the fault process, and effectively update diagnosis model to include new coming abnormal samples and fault classe.

In order to provide more sensitive monitoring results, the time dynamics and steady-state operating conditions should be separately monitored by distinguishing time information from the steady-state counterpart. However, it is a more challenging task for batch processes because they vary from phase to phase presenting multiple steady states and complex dynamic characteristics. To address the above issue, a concurrent monitoring strategy of multiphase steady states and process dynamics is developed for batch processes in this work. On one hand, multiple local models are constructed to identify a steady derivation from the normal operating condition for different phases. On the other hand, based on the recognition that the process dynamics can be considered to be irrelevant with the steady states, a global model is built to detect the dynamics anomalies by monitoring the time variations. Corresponding to alarms issued by different statistics, different operating statuses are indicated with meaningful physical interpretation and deep process understanding. To illustrate the feasibility and efficacy, the proposed algorithm is applied to a typical multiphase batch process, the injection molding process.