| 1. |
-
AI and Learning Systems : Industrial Applications and Future Directions
- 2021
-
Samlingsverk (redaktörskap) (refereegranskat)abstract
- Over the last few years, interest in the industrial applications of AI and learning systems has surged. This book covers the recent developments and provides a broad perspective of the key challenges that characterize the field of Industry 4.0 with a focus on applications of AI. The target audience for this book includes engineers involved in automation system design, operational planning, and decision support. Computer science practitioners and industrial automation platform developers will also benefit from the timely and accurate information provided in this work. The book is organized into two main sections comprising 12 chapters overall:•Digital Platforms and Learning Systems•Industrial Applications of AI
|
|
| 2. |
- Aslanidou, Ioanna, et al.
(författare)
-
Development of web-based short courses on control, diagnostics, and instrumentation
- 2020
-
Ingår i: Proceedings of the ASME Turbo Expo 2020, Sep 21-25. - 9780791884157
-
Konferensbidrag (refereegranskat)abstract
- As a consequence of globalization and advances in digital tools, synchronous or asynchronous distance courses are becoming an integral part of universities’ educational offers. The design of an online course introduces more challenges compared to a traditional on campus course with face to face lectures. This is true especially for engineering subjects where problem or project-based courses may be preferred to stimulate critical thinking and engage the learners with real-life problems. However, realizing this with distance learning implies that a similar study pace should be kept by the learners involved. This may not be easy, since individual pace is often a motivation for choosing a distance course. Student engagement in group projects, collaborations, and the proper design of examination tasks are only some of the challenges in designing a distance course for an engineering program. A series of web-based courses on measurement techniques, control, and diagnostics were developed and delivered to groups of learners. Each course comprised short modules covering key points of the subject and aimed at getting learners to understand both the fundamental concepts that they do not typically learn or understand in the respective base courses and to build on that knowledge to reach a more advanced cognitive level. The experience obtained in the courses on what strategies worked better or worse for the learners is presented in this paper. A comparison between the courses provides an interesting outlook on how the learners reacted to slightly different requirements and incentives in each course. The results from the evaluation of the courses are also used as a base for discussion.The background and availability of the learners is closely linked to how a course should be designed to optimally fit the learning group, without compromising on the achievement of the learning outcomes. This series of courses is a good example of continuous professional development courses in the field of control, diagnostics, and instrumentation (CDI), and brings with it a number of challenges and opportunities for the development of online courses.
|
|
| 3. |
- Aslanidou, Ioanna, et al.
(författare)
-
Micro Gas Turbines in the Future Smart Energy System : Fleet Monitoring, Diagnostics, and System Level Requirements
- 2021
-
Ingår i: Frontiers in Mechanical Engineering. - : Frontiers Media S.A.. - 2297-3079. ; 7
-
Forskningsöversikt (refereegranskat)abstract
- The energy generation landscape is changing, pushed by stricter regulations for emissions control and green energy generation. The limitations of renewable energy sources, however, require flexible energy production sources to supplement them. Micro gas turbine based combined heat and power plants, which are used for domestic applications, can fill this gap if they become more reliable. This can be achieved with the use of an engine monitoring and diagnostics system: real-time engine condition monitoring and fault diagnostics results in reduced operating and maintenance costs and increased component and engine life. In order to allow the step change in the connection of small engines to the grid, a fleet monitoring system for micro gas turbines is required. A proposed framework combines a physics-based model and a data-driven model with machine learning capabilities for predicting system behavior, and includes a purpose-developed diagnostic tool for anomaly detection and classification for a multitude of engines. The framework has been implemented on a fleet of micro gas turbines and some of the lessons learned from the demonstration of the concept as well as key takeaways from the general literature are presented in this paper. The extension of fleet monitoring to optimal operation and production planning in relation to the needs of the grid will allow the micro gas turbines to fit in the future green energy system, connect to the grid, and trade in the energy market. The requirements on the system level for the widespread use of micro gas turbines in the energy system are addressed in the paper. A review of the current solutions in fleet monitoring and diagnostics, generally developed for larger engines, is included, with an outlook into a sustainable future.
|
|
| 4. |
- Aslanidou, Ioanna
(författare)
-
Micro Gas Turbines - Trends and Opportunities
- 2022
-
Ingår i: Mechanical engineering (New York, N.Y. 1919). - : ASME Press. - 0025-6501 .- 1943-5649. ; 61:3, s. 58-60
-
Tidskriftsartikel (refereegranskat)
|
|
| 5. |
- Aslanidou, Ioanna, et al.
(författare)
-
Reforming heat and power technology course structure using student feedback to enhance learning experience
- 2021
-
Ingår i: International Journal of Mechanical Engineering Education. - : SAGE Publications. - 0306-4190 .- 2050-4586. ; 49:4, s. 410-434
-
Tidskriftsartikel (refereegranskat)abstract
- The main outcomes of an engineering course should be for the students to achieve the educational goals, enhance their problem solving capabilities and develop essential skills for their future career. In that context, it is important to understand what motivates the students and what helps them develop an engineering mindset. This paper discusses the improvement of a course with the use of student feedback to motivate students and help them develop essential skills. The purpose of the paper is to provide insight into how different aspects of the course are linked to the students’ growth. Different activities have been integrated in the course over the past years. The effect these have on the student motivation to follow the course and develop skills, knowledge and interest in the subject is discussed through the analysis of student performance, student feedback and the experience of the lecturers. The improvements in the course based on the student feedback were received positively by the students, whose learning experience improved, even though the workload of the course was high. Their motivation to successfully complete the course has also increased through the changes in the delivery of the course and the support by the teachers. The combination of student feedback and teacher experience is key for the improvement of a course, while ensuring that the students develop their engineering knowledge. Therefore, the teachers should strike a balance between helping the students find the solution and encouraging them to think on their own in order to develop essential skills.
|
|
| 6. |
- da Silva, E. R., et al.
(författare)
-
Preliminary design, optimization and CFD analysis of an organic rankine cycle radial turbine rotor
- 2021
-
Ingår i: Applied Thermal Engineering. - : Elsevier Ltd. - 1359-4311 .- 1873-5606. ; 195
-
Tidskriftsartikel (refereegranskat)abstract
- The present study describes the development of a preliminary design of a rotor for a radial turbine operating in an organic Rankine cycle. An optimization algorithm is applied to the preliminary design in order to obtain a better configuration of the geometric parameters that provides good quantification of the efficiency in the turbine, a priori, since the application of optimization processes applied to three-dimensional problems consume a lot of computational resources. The strategy makes it possible to obtain an optimized geometry to obtain flow field analyzes by applying computational fluid dynamics techniques. The working fluid R236fa was used for comparison with the literature, as it presents a positive slope of the saturation curve, and thus it is possible to work with lower temperatures. The R245fa working fluid is more suitable to the operating conditions of the proposed cycle, allows an overpressure in the condenser and allows higher levels of system efficiency. The losses at the rotor nozzle were initially modeled using a mean line design approach. The preliminary design was implemented in a commercial code Matlab®, as well as the optimization algorithm, CRSA (Controlled Random Search Algorithm), and the real gas formulations were used based on the NIST REFPROP® database. The present study is presented under three work routes: i) Development of the preliminary design methodology for a radial turbine that operates with ORC producing 50 kW of power, in order to compare with other methodologies presented in the literature. The results were compared with results observed in the literature, and demonstrate agreement between the reference geometry and the thermodynamic parameters. The total-total efficiencies of the reference turbine designs were 76.23% (R236fa) and 79.28% (R245fa); ii) Optimization by CRSA of the preliminary design of a radial turbine developed on the basis of flow coefficient and load coefficient correlations. A three-dimensional analysis of the flow through the blade section using computational fluid dynamics was performed in the final optimized design to confirm the preliminary design and subsequently analyze its characteristics. The optimization focused on the R245fa working fluid. Although several optimized preliminary designs are available in the literature with efficiency levels of up to 90%, the preliminary design choices made will only be valid for machines operating with ideal gases, that is, exhaust gases typical of an air-breathing combustion engine. For machines operating with real gases, such as organic working fluids, the design options need to be rethought and a preliminary design optimization process must be introduced. As an important result observed, an efficiency of 82.4% was obtained in the final design of the radial turbine operating with R245fa after the optimization process.
|
|
| 7. |
- Dahlquist, Erik, 1951-, et al.
(författare)
-
AI Overview : Methods and Structures
- 2021. - 1
-
Ingår i: AI and Learning Systems - Industrial Applications and Future Directions. - : IntechIntechOpen. - 9781789858778 - 9781839686016
-
Bokkapitel (refereegranskat)abstract
- This paper presents an overview of different methods used in what is normally called AI-methods today. The methods have been there for many years, but now have built a platform of methods complementing each other and forming a cluster of tools to be used to build “learning systems”. Physical and statistical models are used together and complemented with data cleaning and sorting. Models are then used for many different applications like output prediction, soft sensors, fault detection, diagnostics, decision support, classifications, process optimization, model predictive control, maintenance on demand and production planning. In this chapter we try to give an overview of a number of methods, and how they can be utilized in process industry applications.
|
|
| 8. |
- Diamantidou, Eirini, et al.
(författare)
-
A Robust Initialization Approach of Multi-Point Synthesis Schemes For Aero-Engine Conceptual Design
- 2021
-
Ingår i: AIAA Propulsion and Energy Forum, 2021. - Reston, Virginia : American Institute of Aeronautics and Astronautics Inc, AIAA. - 9781624106118
-
Konferensbidrag (refereegranskat)abstract
- During the last years, the aviation industry has shifted its focus towards increasing the aircraft efficiency. The constant drive to search for more efficient systems has led to the introduction of novel concepts. These concepts expand the design space but, at the same time, bring several challenges to the design process. One of the challenges is to develop a conceptual engine design model that can work effectively and provide consistently accurate solutions, even when there are dramatic changes in design constraints. In this work, a multipoint synthesis approach is developed which considers multiple points during the design phase. By incorporating multiple operating points into the design analysis phase, it is ensured that all performance requirements and design constraints are satisfied. A comparison between the traditional engine design approach and the proposed approach is presented to showcase the advantages of the proposed method. A parametric analysis of a geared turbofan configuration is conducted for both design approaches. Then, the multi-point synthesis approach is employed for the design space exploration of a conventional geared turbofan engine and a parallel-hybrid (or boosted) turbofan engine. To enable these studies, surrogate models are developed which utilize machine learning methods in a database of converged engine designs and can ensure the effective and fast operation of the engine model. It is concluded that this surrogate adapted algorithm improves computational efficiency and can be used to evaluate alternative designs.
|
|
| 9. |
- Diamantidou, Eirini, et al.
(författare)
-
Recent Advances in Boundary Layer Ingestion Technology of Evolving Powertrain Systems
- 2022
-
Ingår i: Sustainability. - : MDPI. - 2071-1050. ; 14:3
-
Tidskriftsartikel (refereegranskat)abstract
- The increasing environmental concern during the last years is driving the research community towards reducing aviation’s environmental impact. Several strict goals set by various aviation organizations shifted the research focus towards more efficient and environmentally friendly aircraft concepts. Boundary Layer Ingestion (BLI) is currently investigated as a potential technology to achieve different design goals such as energy efficiency improvement and noise emission reductions in the next generation of commercial aircraft. The technology principle is to place the propulsive unit within the boundary layer generated by the airframe body. Although several studies showed its theoretical benefits, a multidisciplinary nature is introduced in the design phase. This imposes new challenges on the current design tools. An increasing number of publications are focusing on assessing this technology while taking into account interlinks between different disciplines. The goal of this work is to review the current state-of-the-art of BLI evaluation studies. Particular focus is given to the underlying assumptions of each work, the methodology employed, and the level of fidelity of the tools used. By organizing the available work in a comprehensive manner, the up-to-date results are interpreted. The current trends and trade-offs emerging from studies are presented. Through reviewing the ongoing published work, the next steps for further development of the methods that will assess this technology are derived.
|
|
| 10. |
- Fentaye, Amare Desalegn, et al.
(författare)
-
Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks
- 2021
-
Ingår i: Machines. - : MDPI. - 2075-1702. ; 9:12
-
Tidskriftsartikel (refereegranskat)abstract
- The rapid advancement of machine-learning techniques has played a significant role in the evolution of engine health management technology. In the last decade, deep-learning methods have received a great deal of attention in many application domains, including object recognition and computer vision. Recently, there has been a rapid rise in the use of convolutional neural networks for rotating machinery diagnostics inspired by their powerful feature learning and classification capability. However, the application in the field of gas turbine diagnostics is still limited. This paper presents a gas turbine fault detection and isolation method using modular convolutional neural networks preceded by a physics-driven performance-trend-monitoring system. The trend-monitoring system was employed to capture performance changes due to degradation, establish a new baseline when it is needed, and generatefault signatures. The fault detection and isolation system was trained to step-by-step detect and classify gas path faults to the component level using fault signatures obtained from the physics part. The performance of the method proposed was evaluated based on different fault scenarios for a three-shaft turbofan engine, under significant measurement noise to ensure model robustness. Two comparative assessments were also carried out: with a single convolutional-neural-network-architecture-based fault classification method and with a deep long short-term memory-assisted fault detection and isolation method. The results obtained revealed the performance of the proposed method to detect and isolate multiple gas path faults with over 96% accuracy. Moreover, sharing diagnostic tasks with modular architectures is seen as relevant to significantly enhance diagnostic accuracy.
|
|
