High dimension feature extraction based visualized SOM fault diagnosis method and its application in p-xylene oxidation process

Purified terephthalic acid (PTA) is an important chemical raw material. P-xylene (PX) is transformed to terephthalic acid (TA) through oxidation process and TA is refined to produce PTA. The PX oxidation reaction is a complex process involving three-phase reaction of gas, liquid and solid. To monitor the process and to improve the product quality, as well as to visualize the fault type clearly, a fault diagnosis method based on self-organizing map (SOM) and high dimensional feature extraction method, local tangent space alignment (LTSA), is proposed. In this method, LTSA can reduce the dimension and keep the topology information simultaneously, and SOM distinguishes various states on the output map. Monitoring results of PX oxidation reaction process indicate that the LTSA–SOM can well detect and visualize the fault type.

Graphical AbstractWe propose LTSA–SOM to extract the high dimensional data feature and diagnose a PX oxidation reaction process. In the algorithm LTSA–SOM, LTSA can extract feature and reduce dimension while reserving the local geometry in low dimensional space and SOM projects the treated data into a two-dimensional grid and clusters the data. The figure below is the trajectory of fault 6 dataset. In this dataset, the first 10 samples are under normal condition and later 30 samples are under fault 6 condition. Through the figure, we can see the process clearly, the observations are operated in normal area firstly (shown (a)), and as time goes on, the process leaves the normal region and extends to the area of fault 6 state (shown (b)). Thus, for PX oxidation process, the algorithm can monitor the trajectory of whole process timely and achieve fault diagnosis.Figure optionsDownload as PowerPoint slide