Deep Learning Prediction for Rotational Speed of Turbine in Oscillating Water Column-Type Wave Energy Converter

This study uses deep learning algorithms to predict the rotational speed of the turbine generator in an oscillating water column-type wave energy converter (OWC-WEC). The effective control and operation of OWC-WECs remain a challenge due to the variation in the input wave energy and the significantly high peak-to-average power ratio. Therefore, the rated power control of OWC-WECs is essential for increasing the operating time and power output. The existing rated power control method is based on the instantaneous rotational speed of the turbine generator. However, due to physical limitations, such as the valve operating time, a more refined rated power control method is required. Therefore, we propose a method that applies a deep learning algorithm. Our method predicts the instantaneous rotational speed of the turbine generator and the rated power control is performed based on the prediction. This enables precise control through the operation of the high-speed safety valve before the energy input exceeds the rated value. The prediction performances for various algorithms, such as a multi-layer perceptron (MLP), recurrent neural network (RNN), long short-term memory (LSTM), and convolutional neural network (CNN), are compared. In addition, the prediction performance of each algorithm as a function of the input datasets is investigated using various error evaluation methods. For the training datasets, the operation data from an OWC-WEC west of Jeju in South Korea is used. The analysis demonstrates that LSTM exhibits the most accurate prediction of the instantaneous rotational speed of a turbine generator and CNN has visible advantages when the data correlation is low.

Substantiation of the Energy Efficient Schedules of Drying Grain Seeds

It is important to study the patterns of drying grain seeds in order to improve the energy efficiency of the process. Energy efficiency is one of the main parameters that define the choice of a drying schedule. Traditional drying technologies are based on low temperature schedules, which do not allow significantly intensifying the process by increasing the temperature of the heat agent because of substantial reductions in the quality of the material. To adequately assess the drying schedules, we conducted the study of drying grain seeds at low temperatures aimed to preserve the seed properties of the material. To increase the energy efficiency of the drying process, a step-by-step descending low-temperature drying schedule was suggested, which provides for the required quality of seed material. All the proposed technical solutions for the energy-efficient schedules of drying grain seeds were summarized in the recommendations for industrial drying in column type direct-flow grain dryers.

Assessment of the Thermal Radiation Spread in Special Conditions

Increase of the requirements for the safety of hazardous production facilities stimulates the development and improvement of the methodological approaches to accidents consequences assessment on the main gas and other pipelines. Existing models for determining heat fluxes from radiating flame surfaces are focused on assessing damage under standard conditions when the epicenter of the accident is at the same altitude level with potential recipients and there are no barriers between them. In practice, special conditions are often implemented, in particular: fires on the pipelines located in the mountainous areas, safe passage of aircraft near the burning site, protection of objects from thermal radiation by installing impenetrable screens. Approaches are proposed related to assessing heat fluxes at the receiving sites located at different altitude levels with the fire source, as well as during accidents with ignition on the gas pipelines in the presence of screens protecting against thermal radiation. A parameter is introduced that describes the effect of the multilevel location of the source and the recipient on radiation — the coefficient of change in the thermal radiation flux from the side surface of a column-type fire in the absence of a wind, depending on the location height and distance in relation to the ground source of combustion of the site receiving the radiation. An expression is given for determining safe height of the flight of aircraft over a column-type fire in the range of flame heights from 50 to 850 m. Isolines of the fields of heat fluxes from the flame of a high-speed flat jet are calculated when the radiation is screened by a wall located at a normalized distance. The results obtained make it possible to predict the consequences of accidents on the main gas pipelines with gas ignition considering the relief, to assess the boundaries of safe corridors for flights of the aircraft near gas pipelines, and to efficiently develop means of protecting objects surrounding the main pipelines from thermal radiation from a flat torch.

Effects of Influent Concentration and Flow Rate on the Sorption of Diesel Molecules on Kapok Fibers at Dynamic Conditions

Kapok fibers were used as a filtering medium in a column-type filtration set-up to separate diesel from water molecules in dynamic conditions. The amount of diesel flowing out the filtration system with respect to time was monitored. The times wherein the diesel first came out the filtering system (breakthrough time) were shorter at higher influent concentration and faster flow rate. Meanwhile, the total sorbed diesel molecules in the filtering system were increasing with the influent concentration while invariant with flow rate. The shorter breakthrough time was associated with the higher amount of diesel molecules that could be sorbed at a shorter time and the rate at which the overall processes of sorption-desorption-resorption proceeded. On the other hand, the sorption capacity of the system was viewed to be affected by the amount of moving diesel molecules that would interact with the kapok fibers and/or surface-sorbed diesel molecules but not by the contact time.

Analysis of Suspended Potential Discharge Defects by SF6 Decomposition Products

The type and content of SF6 decomposition products are directly related to the type, location and degree of fault. Based on the analysis of the abnormal SF6 gas decomposition product content and discharge type of 126kV Porcelain Column type circuit breaker, the potential fault of the circuit breaker is judged to be suspension potential discharge fault. After disassembling the circuit breaker, it is found that the abnormal phase of the insulation rod is deformed, the pin become thin, and there are solid decomposition products, the sulfides and fluoride, which are mainly composed of iron, aluminum, chromium and manganese, further confirm that the potential fault of the circuit breaker is suspension potential discharge fault. The forming process and reaction mechanism of the suspended potential discharge fault are analyzed. Once the fault occurs, its function will promote the development of the fault. The influence of the suspension potential discharge fault on the performance of the circuit breaker is also analyzed. When the suspension potential discharge fault exists, it will cause the abnormality and even affect the normal operation of the circuit breake.