Real time diagnostics of technological processes and field equipment

Real‐time diagnostics of the olefin production process

“…The monitoring and fault detection procedure will look as follows: To form a sample matrix of the original data X k ( k = 0) with N rows (measurements) and p columns (variables) under normal process conditions (in our case, p = 57 real process variables (temperatures, pressures, flow rates, levels, pressure drops, temperature differences) were taken into account; samples of variables were obtained from the SCADA system of the olefin production plant with a period of 5 min). Then to normalize the matrix to zero mean and unit variance. To form a PCA model by computing matrices of loadings P k and scores T k using either singular decomposition of the covariance matrix of X or the NIPALS algorithm .…”

“…where P includes q loading vectors taken into account in PCA model, Λ = diag{λ 1 , λ 2 , ..., λ q }, and λ i are the eigenvalues of the covariance matrix in descending order, and x is an observation vector of dimension p. If at least one statistics exceeds its threshold, it is indicative of a fault detection. The monitoring and fault detection procedure will look as follows: 6 1. To form a sample matrix of the original data X k (k = 0) with N rows (measurements) and p columns (variables) under normal process conditions (in our case, p = 57 real process variables (temperatures, pressures, flow rates, levels, pressure drops, temperature differences) were taken into account; samples of variables were obtained from the SCADA system of the olefin production plant with a period of 5 min).…”

“…This leads to downtime and economic loss of the enterprise. That is why early detection and prevention of dangerous situations before the emergency shut‐down system actuates is the important task . Technologists and operators solve usually the problem on the basis of their experience.…”

“…That is why early detection and prevention of dangerous situations before the emergency shut-down system actuates is the important task. [4][5][6] Technologists and operators solve usually the problem on the basis of their experience. This method of diagnostics contains however a human factor and requires for new employees to be trained carefully and over a long period of time.…”

Fault diagnosis in chemical processes and equipment with feedbacks

“…DM can be built with different approaches such as quantitative and qualitative relationships, expert systems, neural nets, etc. [1][2][3]. However, the diagnostics of potentially dangerous processes with repeated cycles (recycles) and automatic control equipment in control loops (sensors, actuators, valves, etc.)…”