Multi-mode operation of principal component analysis with k-nearest neighbor algorithm to monitor compressors for liquefied natural gas mixed refrigerant processes

- Propose a framework of process monitoring and fault detection by combining multimode PCA and k-NN mode classification.
- Developed model is applied to monitor the LNG mixed refrigeration process and series of compressors.
- Proposed k-NN integrated multi-mode PCA shows more accurate and early detection capability even under operation mode change situations than conventional PCA.

LNG mixed refrigeration (MR) process is usually used for liquefying natural gas. The compressors for refrigerant compression are associated with the high-speed rotating parts to create a high-pressure. However, any malfunction in the compressors can lead to significant process downtime, catastrophic damage to equipment and potential safety consequences. The existing methodology assumes that the process has a single mode of operation, which makes it difficult to distinguish between a malfunction of the process and a change in mode of operation. Therefore, k-nearest neighbor algorithm (k-NN) is employed to classify the operation modes, which is integrated into multi-mode principal component analysis (MPCA) for process monitoring and fault detection. When the fault detection performance is evaluated with real LNG MR process data, the proposed methodology shows more accurate and early detection capability than conventional PCA. Consequently, proposed k-NN integrated multi-mode PCA methodology will play an important role in monitoring the LNG process.