A Supervised Tensor Dimension Reduction-Based Prognostics Model for Applications with Incomplete Imaging Data
This work addresses prognostic challenges in applications with incomplete imaging data, representing an incremental improvement over existing image-based models.
The paper tackles the problem of prognostic modeling with incomplete tensor imaging data by proposing a supervised dimension reduction method that uses time-to-failure to guide feature extraction, resulting in a model that does not require complete data and enhances prognostic effectiveness.
This paper proposes a supervised dimension reduction methodology for tensor data which has two advantages over most image-based prognostic models. First, the model does not require tensor data to be complete which expands its application to incomplete data. Second, it utilizes time-to-failure (TTF) to supervise the extraction of low-dimensional features which makes the extracted features more effective for the subsequent prognostic. Besides, an optimization algorithm is proposed for parameter estimation and closed-form solutions are derived under certain distributions.