https://www.mdu.se/

The world's oceans, covering approximately 71 % of the Earth's surface, harbor vast wave energy resources, offering a potential solution to the pressing energy crisis and environmental pollution caused by fossil fuel combustion. In recent years, there has been a global surge in exploration and development of wave energy conversion technologies, aimed at effectively harnessing wave energy to realizing sustainable and intelligent sea solutions. This comprehensive review examines the advancements, challenges and future research directions of current mainstream wave energy conversion technologies. Firstly, the distribution of global wave resources and energy conversion process involved in wave energy extraction are analyzed. Subsequently, various wave energy conversion technologies are meticulously classified based on their power take-off systems, and the strengths and challenges of each category are comprehensively investigated. Especially, a universal standard consisting of 5 key indicators has been established to evaluate and compare the characteristics of various wave energy conversion technologies based on different transduction mechanisms, providing comprehensive and intuitive valid references for developers with different needs. The evaluation reveals that the wave energy converters based on hybrid systems demonstrate significant promise as conversion technologies. Moreover, the review presents a summary and analysis of the latest advancements in the application of artificial intelligence within wave energy conversion technologies. This emerging integration of artificial intelligence showcases promising development and potential for further enhancing wave energy conversion systems. Lastly, the review explores the application and future research directions of wave energy conversion technologies. Notably, the investigation highlights the potential of developing a multi-energy complementary power generation system that can concurrently harness multiple renewable energy sources coexisting at sea. This concept represents a promising avenue for future research and development.

Using heat pipes (HPs) is an effective method for heat dissipation to overcome the challenge about the rising power density of the permanent magnet synchronous motor (PMSM). Using machine learning models to evaluate the performance of HPs has attracted much attention. There are many key input features that can affect the performance of machine learning models, which impacts, whereas, have not been understood, and how to select such features still remains unclear. In this work, the impact of thirteen key input features is investigated by using the Shapely value. Results showed that, when only predicting the effective thermal conductivity (Keff), heat flux (Q), ratio of HP length to diameter (F), ratio of evaporator length to HP length (e), ratio of condenser length to HP length (c), ratio of HP length to cross area (I), effective length of HP (Leff), inclination angle (B), and Nusselt number (Nu) should be considered when using the Artificial Neural Network (ANN) model. Based on such input features, the mean absolute percentage error (MAPE) and coefficient of determination (R2) are 5.68 % and 0.9580, respectively. When predicting critical heat flux (Qcr) and (Keff), the model accuracy is lower, with 6.81 % of MAPE and 0.9377 of R2. The identified key input features can also provide insights on how to improve the HP design and how to renovate the development of physical models.

Household consumption accounts for about one-third of global electricity. Accurate results of household load prediction would help in energy management at both the building and the grid levels. Data-driven household load prediction methods have shown great advantages and potential in terms of accuracy. However, these methods still face challenges such as limited data for individual households, diversified electricity consumption behaviors, and data privacy concerns. To solve these problems, this paper proposes a personalized federated learning household load prediction framework (PF-HoLo), which allows personal models to learn collectively, leverages multisource data to capture diverse consumption behaviors, and ensures data privacy. In addition, the global encoder model and mutual learning are proposed to enhance the performance of the PF-HoLo framework considering imbalanced residential historical data. Ablation experiments results prove that the PF-HoLo framework could achieve significant improvements, with 13.41% Mean Square Error and 11.33% Mean Absolute Error, compared to traditional federated learning methods.

Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration of phone-based ambient temperature estimation methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.

Self-powered smart buoys are widely used in sustainable sea, such as marine environmental monitoring. The article designs a self-powered and self-sensing point-absorber wave energy converter based on the two-arm mechanism. The system consists of the wave energy capture module, the power take-off module, the generator module and the energy storage module. As the core component of the wave energy converter, the power take-off module is mainly composed of a two-arm mechanism, which can convert the oscillation heave motion into unidirectional rotary motion. To evaluate the power generation performance of the system, the kinematic and dynamic models of the wave energy converter with the flywheel are established, and the disengagement and engagement phenomena of the flywheel are analyzed. The effectiveness of the prototype in capturing wave energy is verified through dry experiments in lab and field tests. The dry experiment reveals that the maximum output power of the system is 5.67 W, and the maximum and average mechanical efficiency are 66.63 % and 48.35 %, respectively. Additionally, the field test demonstrates that the peak output power can reach 92 W. Meanwhile, the generated electrical signals can be processed by deep learning algorithms to accurately identify different wave states. This high performance confirms that the proposed wave energy converter can meet its own energy needs by capturing wave energy in the marine environment, while also achieving self-sensing for wave condition monitoring. The system has great potential for promoting the development of intelligent sustainable sea in the future. 

Accurate air quality forecasting is crucial for public health, environmental monitoring and protection, and urban planning. However, existing methods fail to effectively utilize multi-scale information, both spatially and temporally. There is a lack of integration between individual monitoring stations and city-wide scales. Temporally, the periodic nature of air quality variations is often overlooked or inadequately considered. To overcome these limitations, we conduct a thorough analysis of the data and tasks, integrating spatio-temporal multi-scale domain knowledge. We present a novel Multi-spatial Multi-temporal air quality forecasting method based on Graph Convolutional Networks and Gated Recurrent Units (M2G2), bridging the gap in air quality forecasting across spatial and temporal scales. The proposed framework consists of two modules: Multi-scale Spatial GCN (MS-GCN) for spatial information fusion and Multi-scale Temporal GRU (MT-GRU) for temporal information integration. In the spatial dimension, the MS-GCN module employs a bidirectional learnable structure and a residual structure, enabling comprehensive information exchange between individual monitoring stations and the city-scale graph. Regarding the temporal dimension, the MT-GRU module adaptively combines information from different temporal scales through parallel hidden states. Leveraging meteorological indicators and four air quality indicators, we present comprehensive comparative analyses and ablation experiments, showcasing the higher accuracy of M2G2 in comparison to nine currently available advanced approaches across all aspects. The improvements of M2G2 over the second-best method on RMSE of 72-h future predictions are as follows: PM2.5: 6%∼10%; PM10: 5%∼7%; NO2: 5%∼16%; O3: 6%∼9%. Furthermore, we demonstrate the effectiveness of each module of M2G2 by ablation study. We conduct a sensitivity analysis of air quality and meteorological data, finding that the introduction of O3 adversely impacts the prediction accuracy of PM2.5.

The abilities to understand pedestrian social interaction behaviors and to predict their future trajectories are critical for road safety, traffic management and more broadly autonomous vehicles and robots. Social interactions are intuitively heterogeneous and dynamic over time and circumstances, making them hard to explain. In this paper, we creatively investigate modeling interpretable social interactions for pedestrian trajectory, which is not considered by the existing trajectory prediction research. Moreover, we propose a two-stage methodology for interaction modeling - “mode extraction” and “mode aggregation”, and develop a long short-term memory (LSTM)-based model for long-term trajectory prediction, which naturally takes into account multi-types of social interactions. Different from previous models that do not explain how pedestrians interact socially, we extract latent modes that represent social interaction types which scales to an arbitrary number of neighbors. Extensive experiments over two public datasets have been conducted. The quantitative and qualitative results demonstrate that our method is able to capture the multi-modality of human motion and achieve better performance under specific conditions. Its performance is also verified by the interpretation of predicted modes, of which the results are in accordance with common sense. Besides, we have performed sensitivity analysis on the crucial hyperparameters in our model. Code is available at: https://github.com/xiaoluban/Modeling-Interpretable-Social-Interactions-for-Pedestrian-Trajectory.

Integrating CO₂ capture with biomass-fired combined heat and power (bio-CHP) plants is a promising method to achieve negative emissions. However, the use of versatile biomass, including waste, and the dynamic operation of bio-CHP plants leads to large fluctuations in the flowrate and CO₂ concentration of the flue gas (FG), which further affect the operation of post-combustion CO₂ capture. To optimize the dynamic operation of CO2 capture, a reliable model to predict the FG flowrate and CO₂ concentration in real time is essential. In this paper, a data-driven model based on the Transformer architecture is developed. The model validation shows that the root mean squared error (RMSE), mean absolute percentage error (MAPE), and Pearson correlation coefficient (PPMCC) of Transformer are 0.3553, 0.0189, and 0.8099 respectively for the prediction of FG flowrate; and 13.137, 0.0318, and 0.8336 respectively for the prediction of CO₂ concentration. The potential impact of various meteorological parameters on model accuracy is also assessed by analyzing the Shapley value. It is found that temperature and direct horizontal irradiance (DHI) are the most important factors, which should be selected as input features. In addition, using the near-infrared (NIR) spectral data as input features is also found to be an effective way to improve the prediction accuracy. It can reduce RMSE and MAPE for CO₂ concentration from 0.2982 to 0.2887 and 0.0158 to 0.0157 respectively, and RMSE and MAPE for FG flowrate from 4.9854 to 4.7537 and 0.0141 to 0.0121 respectively. The Transformer model is also compared to other models, including long short-term memory network (LSTM) and artificial neural network (ANN), which results show that the Transformer model is superior in predicting complex dynamic patterns and nonlinear relationships.

Integrating CO₂ capture with biomass/waste fired combined heat and power plants (CHPs) is a promising method to achieve negative emission. However, the use of versatile biomass/waste and dynamic operation of CHPs result in big fluctuations in the flue gas (FG) and heat input to CO₂ capture. Dynamic modelling is essential to investigate the interactions between key process parameters in producing the dynamic response of the CO₂ capture process. In order to facilitate developing robust control strategies for flexible operation in CO₂ capture plants and optimizing the operation of CO₂ capture plants, artificial intelligence (AI) models are superior to mechanical models due to the easy implementation into the control and optimization. This paper aims to develop an AI model, Informer, to predict the dynamic responses of MEA based CO₂ capture performance from waste-fired CHP plants. Dynamic modelling was first developed in Aspen HYSYS software and validated against the reference. The operation data from the simulated CO₂ capture process was then used to develop and verify Informer. The following variables were employed as inputs: inlet flue gas flow rate, CO₂ concentration in inlet flue gas, lean solvent flow rate, heat input to CO₂ capture. It was found that Informer could predict CO₂ capture rate and energy consumption with the mean absolute percentage error of 6.2% and 2.7% respectively.

Archaeological predictive modeling (APM) is an essential method for quantitatively assessing the probability of archaeological sites present in a region. It is a necessary tool for archaeological research and cultural heritage management. In particular, the predictive modeling process could help us understand the relationship between past human civilizations and the natural environment; moreover, a better understanding of the mechanisms of the human-land relationship can provide new ideas for sustainable development. This study aims to investigate the impact of topographic and hydrological factors on archaeological sites in the Japanese archipelago and Shaanxi Province, China and proposes a hybrid integration approach for APM. This approach employed a conditional attention mechanism (AM) using deep learning and a frequency ratio (FR) model, in addition to a separate FR model and the widely-used machine learning MaxEnt method. The models' outcomes were cross-checked using the four-fold cross-validation method, and the models' performances were compared using the area under the receiver operating characteristic curve (AUC) and Kvamme's Gain. The results showed that in both study areas, the AM_FR model exhibited the most satisfactory performances.