Search

Red imported fire ants (RIFA) are an alien invasive pest that can cause serious ecosystem damage. Timely detection, location and elimination of RIFA nests can further control the spread of RIFA. In order to accurately locate the RIFA nests, this paper proposes an improved deep learning method of YOLOv4. The specific methods were as follows: 1) We improved GhostBottleNeck (GBN) and replaced the original CSP block of YOLOv4, so as to compress the network scale and reduce the consumption of computing resources. 2) An Efficient Channel Attention (ECA) mechanism was introduced into GBN to enhance the feature extraction ability of the model. 3) We used Equalized Focal Loss to reduce the loss value of background noise. 4) We increased and improved the upsampling operation of YOLOv4 to enhance the understanding of multi-layer semantic features to the whole network. 5) CutMix was added in the model training process to improve the model's ability to identify occluded objects. The parameters of improved YOLOv4 were greatly reduced, and the abilities to locate and extract edge features were enhanced. Meanwhile, we used an unmanned aerial vehicle (UAV) to collect images of RIFA nests with different heights and scenes, and we made the RIFA nests (RIFAN) airspace dataset. On the RIFAN dataset, through qualitative analysis of the evaluation indicators, mean average precision (MAP) of the improved YOLOv4 model reaches 99.26%, which is 5.9% higher than the original algorithm. Moreover, compared with Faster R-CNN, SSD and other algorithms, improved YOLOv4 has achieved excellent results. Finally, we transplanted the model to the embedded device Raspberry Pi 4B and assembled it on the UAV, using the model's lightweight and high-efficiency features to achieve flexible and fast flight detection of RIFA nests.

This paper focuses on the power-level control of nuclear power plants (NPPs) in the presence of lumped disturbances. An adaptive second-order nonsingular terminal sliding mode control (ASONTSMC) scheme is proposed by resorting to the second-order nonsingular terminal sliding mode. The pre-existing mathematical model of the nuclear reactor system is firstly described based on point-reactor kinetics equations with six delayed neutron groups. Then, a second-order sliding mode control approach is proposed by integrating a proportional-derivative sliding mode (PDSM) manifold with a nonsingular terminal sliding mode (NTSM) manifold. An adaptive mechanism is designed to estimate the unknown upper bound of a lumped uncertain term that is composed of lumped disturbances and system states real-timely. The estimated values are then added to the controller, resulting in the control system capable of compensating the adverse effects of the lumped disturbances efficiently. Since the sign function is contained in the first time derivative of the real control law, the continuous input signal is obtained after integration so that the chattering effects of the conventional sliding mode control are suppressed. The robust stability of the overall control system is demonstrated through Lyapunov stability theory. Finally, the proposed control scheme is validated through simulations and comparisons with a proportional-integral-derivative (PID) controller, a super twisting sliding mode controller (STSMC), and a disturbance observer-based adaptive sliding mode controller (DO-ASMC).

This paper presents a disturbance observer-based robust backstepping load-following control (DO-RBLFC) scheme for modular high-temperature gas-cooled reactors (MHTGRs) in the presence of actuator saturation and disturbances. Based on reactor kinetics and temperature reactivity feedback, the mathematical model of the MHTGR is first established. After that, a DO is constructed to estimate the unknown compound disturbances including model uncertainties, external disturbances, and unmeasured states. Besides, the actuator saturation is compensated by employing an auxiliary function in this paper. With the help of the DO, a robust load-following controller is developed via the backstepping technique to improve the load-following performance of the MHTGR subject to disturbances. At last, simulation and comparison results verify that the proposed DO-RBLFC scheme offers higher load-following accuracy, better disturbances rejection capability, and lower control rod speed than a PID controller, a conventional backstepping controller, and a disturbance observer-based adaptive sliding mode controller.

The availability of the propulsion system is of primary importance to ensure safe and stable operations of marine crafts, both during transit and station keeping. Diminished propulsion efficiency could impair the ability of a vessel to maintain speed and course and possibly lead to a drifting craft. The waterjet’s propulsion efficiency is affected by several factors such as cavitation, erosion, vibration and noise emission. This paper addresses the design of a fault-tolerant thrust allocation algorithm able to maintain the seaworthiness of a twin-waterjet marine craft in the presence of a severe power loss in one of the waterjets. The proposed solution combines a load torque estimator with an optimization routine that accounts for the power limits when a waterjet is subject to a power loss. This prevents faults from quickly escalating into a complete failure of the waterjet due to excessive power demands. Two simulated case studies including zig-zag path following and sideways movements are presented to demonstrate the effectiveness of the fault tolerant control thrust allocation strategy.

Selective catalytic reduction (SCR) is widely used to remove nitrogen oxides (NOx) in the flue gas of coal-fired power plants. The accumulation of ash particles inside the SCR-deNOx facility will increase the risk of catalyst deactivation or even damage. This paper presents the numerical and experimental investigations on the particle dispersal approach for the SCR-deNOx facility of a 1000 MW coal-fired power plant. The accumulation of different-sized particles is evaluated based on computational fluid dynamics (CFD) simulations. To prevent particles from accumulation, an optimized triangular deflector is proposed and attempts are made to find out the optimal installing position of the deflector. For the π-type SCR-deNOx facilities, the particle accumulation predominantly occurred on one side of the catalysts’ entrance, which corresponds to the inner side of the wedge-shaped turning. It is indicated that particles larger than 8.8 × 10−2 mm are responsible for the significant accumulation. The triangular deflector is proved to be an effective way to reduce particle accumulation and is found most efficient when it is installed at the high-speed area of the vertical duct. Flow model test (FMT) is carried out to validate the dispersal effect for the particle with relatively large sizes and the optimal installing position of the triangular deflector.

Selective catalytic reduction (SCR) is one of the most efficient methods to reduce NOx emissions from coal-fired power plants. This paper deals with an optimal design tower type SCR-deNOx facility for a 1000 MW coal-fired power plant. Combined with computational fluid dynamics (CFD), the configuration of the baffles geometry was studied with spatial constraints. Flow field was regulated at the ammonia injection grid (AIG) with the dual aim of reducing difficulties in implementing the non-uniformed ammonia (NH3) injection strategy and achieving a more homogeneous distribution at the catalyst entrance. A flow model test (FMT) was carried out at a laboratory scale to verify the design results. The results of the flow model test are in good agreement with the computational fluid dynamics. It is indicated that small-sized baffles are recommended for installation at the upstream side of the facility as the optimal design and ability to regulate the flow field at the ammonia injection grid makes it an effective way to deal with spatial constraints. This paper provides a good reference for optimizing the tower type SCR-deNOx facilities with spatial constraints.