Proactive Monitoring Services in Energy Business: Identifying Key Process Areas for Fluidized Bed Boiler Plant Availability Improvement
Eshragh Jahromi, Parsa (2024)
Eshragh Jahromi, Parsa
2024
Master's Programme in Environmental Engineering
Tekniikan ja luonnontieteiden tiedekunta - Faculty of Engineering and Natural Sciences
This publication is copyrighted. Only for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2024-07-29
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202407277768
https://urn.fi/URN:NBN:fi:tuni-202407277768
Tiivistelmä
In the rapidly evolving global energy landscape, this thesis investigates the transformative potential of the industrial internet, specifically proactive monitoring, in enhancing the availability of energy plants. The research aims to identify key operational areas in fluidized bed boiler plants where proactive monitoring can notably enhance the energy plants' availability. It examines potential computational models and algorithms suitable for proactive monitoring purposes, and seeks to understand the necessary features and capabilities of a proactive monitoring tool operating under an industrial internet environment.
The study utilizes a multi-step research strategy that includes a thorough literature review, data collection from a case company, and testing of models and algorithms for proactive monitoring. The validation of these findings and the gathering of additional insights are facilitated through questionnaires and follow-up interviews with energy field experts from the case company.
The study identifies the key process areas and subsystems critical for proactive monitoring in fluidized bed boiler plants. Among the experts interviewed, 85% identified the fuel feeding system as vital, 77% emphasized the furnace’s importance, and 69% highlighted the significance of superheaters. Furthermore, the study highlights the key process parameters that are best suited for proactive monitoring. A substantial 89% of experts advocate for the monitoring of flue gas parameters, mainly through static limit approaches. Similarly, 72% emphasize the importance of tracking rotating equipment parameters, primarily using the long-term deviation approaches. Furthermore, 61% of experts deem it crucial to track bed conditions, likewise using the long-term deviation approaches in conjunction with the static limit approaches. The study emphasizes the importance of continuous monitoring and tracking of the aforementioned key parameters alongside a variety of other process parameters, highlighting the potential benefits of proactive monitoring.
The expert interviews also assess the applicability of various proactive monitoring approaches, with long-term change detection emerging as the most favoured overall. The study also highlights key features and requirements for a proactive monitoring tool, emphasizing customizability and maturity, detailed visualisations of incidents, controlled notification frequency, and insight gathering and clear communication with the customer. The main users for the tool are identified to be process specialists as well as experts responsible for monitoring specific plants.
The study recommends future research to include testing of proactive monitoring approaches on historical real-life cases, inclusion of energy sector customers as part of the information gathering interviews, and development and testing of the proactive monitoring tool on the case company’s industrial internet platform. It also suggests implementing the identified parameters for proactive monitoring as early as possible, continuously monitoring advancements in machine learning and artificial intelligence, and applying the methodology and findings from this study to other sectors in which the case company operates. This approach ensures that the research findings are not only relevant but also actionable, paving the way for significant advancements in the field of proactive monitoring in energy plants.
The study utilizes a multi-step research strategy that includes a thorough literature review, data collection from a case company, and testing of models and algorithms for proactive monitoring. The validation of these findings and the gathering of additional insights are facilitated through questionnaires and follow-up interviews with energy field experts from the case company.
The study identifies the key process areas and subsystems critical for proactive monitoring in fluidized bed boiler plants. Among the experts interviewed, 85% identified the fuel feeding system as vital, 77% emphasized the furnace’s importance, and 69% highlighted the significance of superheaters. Furthermore, the study highlights the key process parameters that are best suited for proactive monitoring. A substantial 89% of experts advocate for the monitoring of flue gas parameters, mainly through static limit approaches. Similarly, 72% emphasize the importance of tracking rotating equipment parameters, primarily using the long-term deviation approaches. Furthermore, 61% of experts deem it crucial to track bed conditions, likewise using the long-term deviation approaches in conjunction with the static limit approaches. The study emphasizes the importance of continuous monitoring and tracking of the aforementioned key parameters alongside a variety of other process parameters, highlighting the potential benefits of proactive monitoring.
The expert interviews also assess the applicability of various proactive monitoring approaches, with long-term change detection emerging as the most favoured overall. The study also highlights key features and requirements for a proactive monitoring tool, emphasizing customizability and maturity, detailed visualisations of incidents, controlled notification frequency, and insight gathering and clear communication with the customer. The main users for the tool are identified to be process specialists as well as experts responsible for monitoring specific plants.
The study recommends future research to include testing of proactive monitoring approaches on historical real-life cases, inclusion of energy sector customers as part of the information gathering interviews, and development and testing of the proactive monitoring tool on the case company’s industrial internet platform. It also suggests implementing the identified parameters for proactive monitoring as early as possible, continuously monitoring advancements in machine learning and artificial intelligence, and applying the methodology and findings from this study to other sectors in which the case company operates. This approach ensures that the research findings are not only relevant but also actionable, paving the way for significant advancements in the field of proactive monitoring in energy plants.