| 1. |
- Ahlgren, Fredrik, 1980-, et al.
(author)
-
Auto Machine Learning for predicting Ship Fuel Consumption
- 2018
-
In: Proceedings of ECOS 2018 - the 31st International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems. - Guimarães. - 9789729959646
-
Conference paper (peer-reviewed)abstract
- In recent years, machine learning has evolved in a fast pace as both algorithms and computing power are constantly improving. In this study, a machine learning model for predicting the fuel oil consumption from engine data has been developed for a cruise ship operating in the Baltic Sea. The cruise ship is equipped with legacy volume flow meters and newly installed mass flow meters, as well as an extensive set of logged time series data from the machinery logging system. The model is developed using state-of-the-art Auto Machine Learning tools, which optimises both the model hyper parameters and the model selection by using genetic algorithms. To further increase the model accuracy, a pipeline of different models and pre-processing algorithms is evaluated. An extensive model trained for a certain system can be used for optimisation simulation, as well as online energy efficiency prediction. As the models automatically adapt to noisy sensor data and thus function as a watermark of the machinery system, these algorithms show a potential in predicting ship energy efficiency without installation of additional mass flow meters. All tools used in this study are Open Source tools written in Python and can be applied on board. The study shows great potential for utilising large amounts of already available sensor data for improving the accuracy of the predicted ship energy consumption.
|
|
| 2. |
- Ahlgren, Fredrik, 1980-, et al.
(author)
-
Energy integration of organic rankine cycle, exhaust gas recirculation and scrubber
- 2018
-
In: Trends and challenges in maritime energy management. - Cham, Switzerland : Springer. - 9783319745756 - 9783319745763 ; , s. 157-168
-
Book chapter (peer-reviewed)abstract
- The vast majority of ships trafficking the oceans are fuelled by residual oil with high content of sulphur, which produces sulphur oxides (SOx) when combusted. Additionally, the high pressures and temperatures in modern diesel engines also produce nitrogen oxides (NOx). These emissions are both a hazard to health and the local environment, and regulations enforced by the International Maritime Organization (IMO) are driving the maritime sector towards the use of either distillate fuels containing less sulphur, or the use of exhaust gas cleaning devices.TwocommontechniquesforremovingSOx andlimitingNOx aretheopen loop wet scrubber and exhaust gas recirculation (EGR). A scrubber and EGR installation reduces the overall efficiency of the system as it needs significant pumping power, which means that the exhaust gases are cleaner but at the expense of higher CO2 emissions. In this paper we propose a method to integrate an exhaust gas cleaning device for both NOx and SOx with an organic Rankine cycle for waste heat recovery, thereby enhancing the system efficiency. We investigate three ORC configurations, integrated with the energy flows from both an existing state-of-the-art EGR system and an additional open loop wet scrubber.
|
|
| 3. |
- Ahlgren, Fredrik, 1980-, et al.
(author)
-
Predicting dynamic fuel oil consumption on ships with automated machine learning
- 2019
-
In: Innovative Solutions for Energy Transitions. - : Elsevier. ; 158, s. 6126-6131
-
Conference paper (peer-reviewed)abstract
- This study demonstrates a method for predicting the dynamic fuel consumption on board ships using automated machine learning algorithms, fed only with data for larger time intervals from 12 hours up to 96 hours. The machine learning algorithm trained on dynamic data from shorter time intervals of the engine features together with longer time interval data for the fuel consumption. To give the operator and ship owner real-time energy efficiency statistics, it is essential to be able to predict the dynamic fuel oil consumption. The conventional approach to getting these data is by installing additional mass flow meters, but these come with added cost and complexity. In this study, we propose a machine learning approach using auto machine learning optimisation, with already available data from the machinery logging system.
|
|
| 4. |
- Ahlgren, Fredrik, 1980-
(author)
-
Reducing ships' fuel consumption and emissions by learning from data
- 2018
-
Doctoral thesis (other academic/artistic)abstract
- In the context of reducing both greenhouse gases and hazardous emissions, the shipping sector faces a major challenge as it is currently responsible for 11% of the transport sector’s anthropogenic greenhouse gas emissions. Even as emissions reductions are needed, the demand for the transport sector rises exponentially every year. This thesis aims to investigate the potential to use ships’ existing internal energy systems more efficiently. The thesis focusses on making existing ships in real operating conditions more efficient based logged machinery data. This dissertation presents results that can make ship more energy efficient by utilising waste heat recovery and machine learning tools. A significant part of this thesis is based on data from a cruise ship in the Baltic Sea, and an extensive analysis of the ship’s internal energy system was made from over a year’s worth of data. The analysis included an exergy analysis, which also considers the usability of each energy flow. In three studies, the feasibility of using the waste heat from the engines was investigated, and the results indicate that significant measures can be undertaken with organic Rankine cycle devices. The organic Rankine cycle was simulated with data from the ship operations and optimised for off-design conditions, both regarding system design and organic fluid selection. The analysis demonstrates that there are considerable differences between the real operation of a ship and what it was initially designed for. In addition, a large two-stroke marine diesel was integrated into a simulation with an organic Rankine cycle, resulting in an energy efficiency improvement of 5%. This thesis also presents new methods of employing machine learning to predict energy consumption. Machine learning algorithms are readily available and free to use, and by using only a small subset of data points from the engines and existing fuel flow meters, the fuel consumption could be predicted with good accuracy. These results demonstrate a potential to improve operational efficiency without installing additional fuel meters. The thesis presents results concerning how data from ships can be used to further analyse and improve their efficiency, by using both add-on technologies for waste heat recovery and machine learning applications.
|
|
| 5. |
- Ahlgren, Fredrik, 1980-
(author)
-
Waste heat recovery in a cruise vessel
- 2016
-
Licentiate thesis (other academic/artistic)abstract
- In three studies of a cruise ship the author has investigated waste heat recovery (WHR)from exhaust gases using an organic Rankine cycle (ORC), and also mapped the energyand exergy flows within the ship. Data were collected from the ship’s machinerysystem for a total extent of one year, and this data were used for simulations andenergy calculations. An off-design analysis was made and an ORC was simulated andoptimised with regards to the ship’s operating conditions. The ORC working fluid wasoptimised in terms for maximum electrical production in the off-design condition. Theoff-design analysis showed that the ship speed and power consumption was far fromits original design. The results indicate that there is a potential for significant savingsby using an organic Rankine cycle for waste heat recovery. The energy and exergyanalysis gave a better understanding of the energy flows and showed that the singlelargest exergy destruction occurs in the ship’s diesel engines.
|
|
| 6. |
- Ahlgren, Fredrik, 1980-, et al.
(author)
-
Waste Heat Recovery in a Cruise Vessel in the Baltic Sea by Using an Organic Rankine Cycle : A Case Study
- 2015
-
In: ASME Turbo Expo 2015: Turbine Technical Conference and Exposition. - : ASME Press. - 9780791856673 ; , s. 43392-43416
-
Conference paper (peer-reviewed)abstract
- Maritime transportation is a significant contributor to SOx, NOx and particle matter emissions, even though it has a quite low CO2 impact. New regulations are being enforced in special areas that limit the amount of emissions from the ships. This fact, together with the high fuel prices, is driving the marine industry towards the improvement of the energy efficiency of current ship engines and the reduction of their energy demand. Although more sophisticated and complex engine designs can improve significantly the efficiency of the energy systems in ships, waste heat recovery arises as the most influent technique for the reduction of the energy consumption. In this sense, it is estimated that around 50% of the total energy from the fuel consumed in a ship is wasted and rejected in fluid and exhaust gas streams. The primary heat sources for waste heat recovery are the engine exhaust and the engine coolant. In this work, we present a study on the integration of an organic Rankine cycle (ORC) in an existing ship, for the recovery of the main and auxiliary engines exhaust heat. Experimental data from the operating conditions of the engines on the M/S Birka Stockholm cruise ship were logged during a port-to-port cruise from Stockholm to Mariehamn over a period of time close to one month. The ship has four main engines Wärtsilä 5850 kW for propulsion, and four auxiliary engines 2760 kW used for electrical consumers. A number of six load conditions were identified depending on the vessel speed. The speed range from 12–14 knots was considered as the design condition, as it was present during more than 34% of the time. In this study, the average values of the engines exhaust temperatures and mass flow rates, for each load case, were used as inputs for a model of an ORC. The main parameters of the ORC, including working fluid and turbine configuration, were optimized based on the criteria of maximum net power output and compactness of the installation components. Results from the study showed that an ORC with internal regeneration using benzene would yield the greatest average net power output over the operating time. For this situation, the power production of the ORC would represent about 22% of the total electricity consumption on board. These data confirmed the ORC as a feasible and promising technology for the reduction of fuel consumption and CO2 emissions of existing ships.
|
|
| 7. |
- Ahlgren, Fredrik, 1980-, et al.
(author)
-
Waste Heat Recovery in a Cruise Vessel in the Baltic Sea by Using an Organic Rankine Cycle : A Case Study
- 2016
-
In: Journal of engineering for gas turbines and power. - : ASME Press. - 0742-4795 .- 1528-8919. ; 138:1
-
Journal article (peer-reviewed)abstract
- Maritime transportation is a significant contributor to SOx,NOx, and particle matter (PM) emissions, and to a lesser extent, of CO2. Recently, new regulations are being enforced in special geographical areas to limit the amount of emissions from the ships. This fact, together with the high fuel prices, is driving the marine industry toward the improvement of the energy efficiency of ships. Although more sophisticated and complex engine designs can improve significantly of the energy systems on ships, waste heat recovery arises as the most effective technique for the reduction of the energy consump- tion. In this sense, it is estimated that around 50% of the total energy from the fuel con- sumed in a ship is wasted and rejected through liquid and gas streams. The primary heat sources for waste heat recovery are the engine exhaust and coolant. In this work, we present a study on the integration of an organic Rankine cycle (ORC) in an existing ship, for the recovery of the main and auxiliary engines (AE) exhaust heat. Experimental data from the engines on the cruise ship M/S Birka Stockholm were logged during a port-to- port cruise from Stockholm to Mariehamn, over a period of 4 weeks. The ship has four main engines (ME) W€artsil€ a 5850kW for propulsion, and four AE 2760kW which areused for electrical generation. Six engine load conditions were identified depending on the ship’s speed. The speed range from 12 to 14 kn was considered as the design condi- tion for the ORC, as it was present during more than 34% of the time. In this study, the average values of the engines exhaust temperatures and mass flow rates, for each load case, were used as inputs for a model of an ORC. The main parameters of the ORC, including working fluid and turbine configuration, were optimized based on the criteria of maximum net power output and compactness of the installation components. Results from the study showed that an ORC with internal regeneration using benzene as working fluid would yield the greatest average net power output over the operating time. For this situation, the power production of the ORC would represent about 22% of the total elec- tricity consumption on board. These data confirmed the ORC as a feasible and promisingtechnology for the reduction of fuel consumption and CO2 emissions of existing ships.
|
|
| 8. |
- Arunachalam, Prakash, et al.
(author)
-
Humid Air Motor : A Novel Concept to Decrease the Emissions Using the Exhaust Heat
- 2017
-
In: SAE Technical Papers. - 400 Commonwealth Drive, Warrendale, PA, United States : SAE International. - 0148-7191. ; 2017-October
-
Journal article (peer-reviewed)abstract
- Humid air motor (HAM) is an engine operated with humidified inlet charge. System simulations study on HAM showed the waste heat recovery potential over a conventional system. An HAM setup was constructed, to comprehend the potential benefits in real-time, the HAM setup was built around a 13-litre six cylinder Volvo diesel engine. The HAM engine process is explained in detail in this paper. Emission analysis is also performed for all three modes of operation. The experiments were carried out at part load operating point of the engine to understand the effects of humidified charge on combustion, efficiency, and emissions. Experiments were conducted without EGR, with EGR, and with humidified inlet charge. These three modes of operation provided the potential benefits of each system. Exhaust heat was used for partial humidification process. Results show that HAM operation, without compromising on efficiency, reduces NOx and soot significantly over the engine operated without EGR. With HAM around 75-80% of the otherwise waste heat is recuperated (Appendix). This heat is used to reduce the pumping losses and emissions unlike in other waste heat recovery technologies, where the power production is the primary objective.
|
|
| 9. |
- Bahrami, Saeed, et al.
(author)
-
Identifying a simplified model for heavy duty gas turbine
- 2014
-
In: Journal of Mechanical Science and Technology. - : Springer Science and Business Media LLC. - 1738-494X .- 1976-3824. ; 28:6, s. 2399-2408
-
Journal article (peer-reviewed)abstract
- A dynamic model was developed for long-term simulation of a heavy duty gas turbine. The model includes the essential control algorithm of the gas turbine as well as the most common outputs and other important intermediate variables. Control algorithm details, such as wind up protection and load limiter algorithm which have large effect on gas turbine transient behavior, are included. The model parameters are identified by applying genetic algorithm and least squares algorithm on regular operational data from a real plant to better match the model response to the real plant. The simulation results have been validated with real plant data and shown to have valid accuracy for many engineering applications.
|
|
| 10. |
- Bahrami, Saeed, et al.
(author)
-
Improving the Transient Performance of the Gas Turbine by Steam Injection during Frequency Dips
- 2013
-
In: Energies. - : MDPI AG. - 1996-1073. ; 6:10, s. 5283-5296
-
Journal article (peer-reviewed)abstract
- Single-shaft gas turbines are sensitive to frequency changes which might affect the grid stability during large frequency drops. This paper presents a new control system that uses steam injection as an auxiliary input to improve the transient performance of the gas turbine during frequency drops. Steam injection is beneficial because it reduces the peak temperature in the combustion chamber and augments the output power by increasing the mass flow through the turbine. The use of this auxiliary input is based on the event-based control approach. It means that during the frequency drop, the controller exploits the steam injection to help the main control loop recover the frequency and when the frequency reaches its predefined value, the system will return to its normal operation. The performance of the proposed control algorithm is investigated under different scenarios and the results show that the application of steam injection improves the performance of the regular control algorithm significantly, especially near full load condition.
|
|
