Purpose: The purpose of this paper is to present a method for monitoring transient thermal stresses. This paper also presents the analysis of thermal stresses of boiler pressure element heating during the start-up in real conditions. The inverse methods are used to determine the wall temperature, whereas the commercial software ANSYS is used to determine the thermal stresses in the pressure component. Design/methodology/approach: The method is based on the solution of the inverse heat conduction problem. Thermal stresses are determined indirectly taking into account the measured temperature values at selected points on the outer wall of a pressure component. First, the transient temperature distribution in the entire pressure element is calculated, and then, thermal stresses are determined by the finite element method. Measured pressure changes are used to determine the stresses resultant from the internal pressure. Findings: The obtained stresses and temperature in the thick-walled pipe are illustrated and compared with experimental data. Satisfactory agreement was found between computational and experimental results. Originality/value: The method can be used in the monitoring of thermal and mechanical stresses during the boiler’s start-up and shut-down. Because the temperature distribution at each time level is determined, it can be applied as a thermal load during the structural analysis.

Modern industries encourages the use of hydrogen as an energy carrier to decarbonize the electricity grid, Polymeric Electrolyte membrane fuel cell which uses hydrogen as a fuel to produce electricity, is an efficient and reliable ‘power to gas’ technology. However, a key issue obstructing the advancement of PEMFCs is the unpredictability of their performance and failure events caused by flooding and dehydration. The accurate prediction of these two events is required to avoid any catastrophic failure in the cell. A typical approach used to predict failure modes relies on modeling failure-induced performance losses and monitoring the voltage of a cell. Data-driven machine learning models must be developed to address these challenges. Herein, we present a machine learning model for the prediction of the failure modes of operating cells. The model predicted the relative humidity of a cell by considering the cell voltage and current density as the input parameters. Advanced regression techniques, such as support vector machine, decision tree regression, random forest regression and artificial neural network, were used to improve the predictions. Features related to the model were derived from cell polarization data. The model’s results were validated with real-time test data obtained from the cell. The statistical machine learning models accurately provided information on the flooding- and dehydration-induced failure events.

Two methods for monitoring the thermal stresses in pressure components of thermal power plants are presented. In the first method, the transient temperature distribution in the pressure component is determined by measuring the transient wall temperature at several points located on the outer insulated surface of the component. The transient temperature distribution in the pressure component, including the temperature of the inner surface is determined from the solution of the inverse heat conduction problem (IHCP). In the first method, there is no need to know the temperature of the fluid and the heat transfer coefficient. In the second method, thermal stresses in a pressure component with a complicated shape are computed using the finite element method (FEM) based on experimentally estimated fluid temperature and known heat transfer coefficient. A new thermometer with good dynamic properties has been developed and applied in practice, providing a much more accurate measurement of the temperature of the flowing fluid in comparison with standard thermometers. The heat transfer coefficient on the inner surface of a pressure element can be determined from the empirical relationships available in the literature. A numerical-experimental method of determination of the transient heat transfer coefficient based on the solution of the 3D-inverse heat conduction problem has also been proposed. The heat transfer coefficient on the internal surface of a pressure element is determined based on an experimentally determined local transient temperature distribution on the external surface of the element or the basis of wall temperature measurement at six points located near the internal surface if fluid temperature changes are fast. Examples of determining thermal and pressure stresses in the thick-walled horizontal superheater header and the horizontal header of the steam cooler in a power boiler with the use of real measurement data are presented.