No abstract

Blade damage accounts for a substantial part of all failure events occurring at gas-turbine-engine power plants. Current operation and maintenance (O&M) practices typically use preventive maintenance approaches with fixed intervals, which involve high costs for repair and replacement activities, and substantial revenue losses. The recent development and evolution of condition-monitoring techniques and the fact that an increasing number of turbines in operation are equipped with online monitoring systems offer the decision maker a large amount of information on the blades’ structural health. So, predictive maintenance becomes feasible. It has the potential to predict the blades’ remaining life in order to support O&M decisions for avoiding major failure events. This paper presents a surrogate model and methodology for estimating the remaining life of a turbine blade. The model can be used within a predictive maintenance decision framework to optimize maintenance planning for the blades’ lifetime.

The main focus of this work is simulation-driven product development methodology for MSc students education. The educational process is built around real product development process; small Unmanned Aerial Vehicle is used as a case-study. The bunch of simulation and optimization tools (NX CAD, Simcenter 3D, LMS System Synthesis, LMS Amesim, ANSYS, STAR-CCM) is used in the educational process for creating so-called digital twin of a real product and to achieve the continuity and transparency of the development process. Product Lifecycle Management (PLM) system is used to manage requirements, changes and integrate all simulation results. The global trend in engineering education is in the transition from the training of narrowly specialized engineers for high-tech industries. In the new reality, the industry needs specialists with broad knowledge and system thinking, which are able to solve problems that require cross-disciplinary expertise. These specialists should be able to use the most advanced methods and tools of numerical simulation, optimization, product lifecycle management, configuration management, advanced manufacturing techniques. The aim is to enhance the classical methodology for systems engineering with a digital environment in order to develop an MSc level courses teaching latest practices for innovative product design based on real case problems. A modeling of the system to be developed enables the comprehensive analysis and its quantitative assessment. Such approach demonstrates both a thorough investigation of a problem and quantitative estimation of the systems efficiency.

No abstract

This paper presents a methodology for predictive and prescriptive analytics of a gas turbine. The methodology is based on a combination of physics-based and data-driven modeling using machine learning techniques. Combining these approaches results in a set of reliable, fast, and continuously updating models for prescriptive analytics. The methodology is demonstrated with a case study of a jet-engine power plant preventive maintenance and diagnosis of its flame tube. The developed approach allows not just to analyze and predict some problems in the combustion chamber, but also to identify a particular flame tube to be repaired or replaced and plan maintenance actions in advance.