REDUCING FUEL USAGE AND CO2 EMISSIONS FROM TUG BOAT FLEETS: SEA TRIALS AND THEORETICAL MODELLING

Sea trials on a harbour tug have been conducted and are explained. The experimental results for fuel consumption per unit transport effort, under free-running (transiting) conditions, are presented and engine speed-propulsor pitch combinations for improved fuel economy are identified. A simplified analytical approach to predict fuel consumption, including the coupled engine-propulsor-hull system, is described. This rationale is combined with experimental observations and, consequently, performance maps present the complete operating envelopes of the harbour tug under both free-running and towing conditions. This combined approach proved to be effective and can be applied to the study of other tug vessels. As a consequence of this research, the engine control system on the harbour tug was modified to permit it to operate fully within the region of best fuel economy during free-running. The results from the bollard-pull predictions provide insight for the design and operation of harbour tugs in the future.

Aero-engine acceleration control using deep reinforcement learning with phase-based reward function

In this paper, the conventional aero-engine acceleration control task is formulated into a Markov Decision Process (MDP) problem. Then, a novel phase-based reward function is proposed to enhance the performance of deep reinforcement learning (DRL) in solving feedback control tasks. With that reward function, an aero-engine controller based on Trust Region Policy Optimization (TRPO) is developed to improve the aero-engine acceleration performance. Four comparison simulations were conducted to verify the effectiveness of the proposed methods. The simulation results show that the phase-based reward function helps to eliminate the oscillation problem of the aero-engine control system, which is caused by the traditional goal-based reward function when DRL is applied to the aero-engine control. And the TRPO controller outperforms deep Q-learning (DQN) and the proportional-integral-derivative (PID) in the aero-engine acceleration control task. Compared to DQN and PID controller, the acceleration time of aero-engine is decreased by 0.6 and 2.58 s, respectively, and the aero-engine acceleration performance is improved by 16.8 and 46.4 % each.

COLLECTOR ENGINE CONTROL SYSTEM

One of the main features of the current stage of scientific and technological progress is the wider use of microelectronics in various sectors of the economy, which is constantly growing. The role of microelectronics in the development of social production is determined by its almost unlimited possibilities in solving various problems in all sectors of the economy, its profound impact on the culture and life of modern man. Particular attention is now paid to the introduction of microprocessors that solve the problem of automation of control of mechanisms, devices and equipment. Adapting the microprocessor to the conditions of a particular task is mostly done by developing appropriate software, which is then stored in program memory. Hardware adaptation in most cases is performed by connecting the necessary integrated circuits and I / O that meet the problem to be solved. In the given work the microprocessor system of regulation of turns of the collector motor of a direct current is developed. The microprocessor system is developed on the basis of the KM1816 BE 51 microprocessor using a DAC. The microprocessor program changes the engine speed in the range from 1000 to 3000 rpm. In microprocessor technology there is an independent class of large integrated circuits (BIS) - single-chip microcomputers (OMEOM), which are designed to "intellectualize" devices for various purposes. The architecture of single-chip microcomputers is the result of the evolution of microprocessors and microprocessor systems, due to the desire to significantly reduce their hardware costs and cost. Typically, these goals are achieved both by increasing the integration of the BIS and by finding a compromise between cost, hardware costs and technical characteristics of the OMEOM. Development of control systems on single-chip microcomputers is one of the most promising areas in the field of process automation, control and management.

The Concept of Networked Distributed Engine Control System of Future Air Vehicles

This report is considered different aspects of the concept of the networked distributed engine control system (DECS) of future air vehicles. These aspects include the following: the structure of multiple networks similar to NATO Generic Vehicle Architecture (NGVA), the role of Artificial Intelligence (AI) in DECS, and the use Augmented Reality (AR) as Human-Machine Interface between AI and pilots. Deployment of AI solutions for monitoring equipment in on-board infrastructure can be provided on physical or virtual servers and in the clouds. In this case, it is possible to use various methods of alerting the pilot and ground personnel on the basis of AR. The use of AI allows covering an unlimited set of scenarios, to provide an assessment of the likelihood of equipment failure, classification alarm is normal, and recognition of the development of defects. To collect Big Data from sensors and the pre-processing of this data before a machine learning (ML) procedure it is proposed to form data sets with the help of the face-splitting matrix product. To decrease the time of reaction of Neural Networks it has been suggested the implementation of advanced tensor-matrix theory on the basis of penetrating face product of matrices. Other important results of the report are a possible version of the AR data format for DECS and a proposal about the use of non-orthogonal frequency discrete multiplexing (N-OFDM) signals to data transfer via fibre optics.

Estimation of Cumulative Noise Reduction at Certification Points for Supersonic Civil Aeroplane Using the Programmed Thrust Management at Take-off and Approach

The reduction of the cumulative noise level at certification points applying to the supersonic civil aeroplane is estimated in the paper. The reduction is obtained by using an programmed thrust management with Programmed Lapse Rate based on the variation of engine power setting at take-off and approach. The use of proposed programmed reduced noise thrust management requires a change of the conventional noise certification procedures as well as further implementation as fully automated system (Variable Noise Reduction System) into aircraft/engine control system. The main engine noise sources such as the fan and exhaust jet are taken into account in the estimation. It is shown that the cumulative noise level using proposed programmed thrust management is lower by 10.7–12.2 EPNdB than using the conventional engine thrust control as currently applied to subsonic jet aeroplanes at take-off and approach.

WIRELESS-BASED TECHNOLOGY FOR OPTIMIZING OF OPERATION OF THE AVIATION ENGINE CONTROL SYSTEM

An approach for improving of efficiency the operation of distributed control system of aviation engine based on wireless technology with high productivity and resolution of wave distributed surface has been presented. It can be applied for development of new principles of correct location the nodes, including the data processing equipment, the intellectual sensors, actuators, repeaters, central units in adaptive control strategies of aviation engine. The optimization method for processing information, using adaptive wavelet filters, as an optimal filter, that minimizes the average square of a common error for organizing the connection between wireless elements in the control systems of aviation gas turbine engine, has been considered, on the theoretical point of view. Also, the wavelets applications in the Wireless Distributed Automatic Control System (WDACS) for aviation engine, the requirements for the construction of its node, supported by the protocol stack, the scheme and the programs with a combination of connections the information exchange between elements have been considered, from the practical point of view.

FDIA System for Sensors of the Aero-Engine Control System Based on the Immune Fusion Kalman Filter

The Kalman filter plays an important role in the field of aero-engine control system fault diagnosis. However, the design of the Kalman filter bank is complex, the structure is fixed, and the parameter estimation accuracy in the non-Gaussian environment is low. In this study, a new filtering method, immune fusion Kalman filter, was proposed based on the artificial immune system (AIS) theory and the Kalman filter algorithm. The proposed method was used to establish the fault diagnosis, isolation, and accommodation (FDIA) system for sensors of the aero-engine control system. Through a filtering calculation, the FDIA system reconstructs the measured parameters of the faulty sensor to ensure the reliable operation of the aero engine. The AIS antibody library based on single sensor fault was constructed, and with feature combination and library update, the FDIA system can reconstruct the measured values of multiple sensors. The evaluation of the FDIA system performance is based on the Monte Carlo method. Both steady and transient simulation experiments show that, under the non-Gaussian environment, the diagnosis and isolation accuracy of the immune fusion Kalman filter is above 95%, much higher than that of the Kalman filter bank, and compared with the Kalman particle filter, the reconstruction value is smoother, more accurate, and less affected by noise.