Search

Abstract Due to the lack of sufficient labeled data for the prostate and the extensive and complex semantic information in ultrasound images, accurately and quickly segmenting the prostate in transrectal ultrasound (TRUS) images remains a challenging task. In this context, this paper proposes a solution for TRUS image segmentation using an end-to-end bidirectional semantic constraint method, namely the BiSeC model. The experimental results show that compared with classic or popular deep learning methods, this method has better segmentation performance, with the Dice Similarity Coefficient (DSC) of 96.74% and the Intersection over Union (IoU) of 93.71%. Our model achieves a good balance between actual boundaries and noise areas, reducing costs while ensuring the accuracy and speed of segmentation.

To mitigate the pressure on energy storage and enhance the flexibility of the power system, lithium-ion batteries are widely utilized in large-scale energy storage in smart grids due to their superior charging and discharging performance and energy storage characteristics. Whereas the inconsistency of lithium battery cells has become a key issue that limits the overall performance of the battery pack. A novel flexible equalization converter is proposed to handle this issue. This converter is combined with a staggered parallel topology and jumper switched, which enables an energy transfer path to exist between any cell to the rest pack and any substring to the rest substring. The electromagnetic transient model and its small-signal model of the proposed converter have been developed in MATLAB to prove its effectiveness. Finally, the conclusion could be arrived at that the proposed topology shows a better performance compared to the traditional method.

Highly efficient maintenance and control of the deep strong mining roadway’s stability is a reliable guarantee for the safe production and sustainable development of a coal mine. With return air roadway 4106 in Wenjiapo coal mine as the research background, an in situ investigation, numerical simulation, and engineering practice were carried out to reveal the stress distribution and surrounding rock deformation and failure characteristics of a strong mining roadway. The numerical simulation results show that both first mining and secondary mining are positively correlated with the deformation and failure of roadway surrounding rock. The peak abutment pressure of the coal pillar near the goaf caused by first mining and secondary mining are 28.7 and 35.6 MPa, respectively, with a 24% increase. During the first mining period, the total deformation of the roof and floor of the roadway and the two sides was 1160 and 1436 mm, respectively. During the second mining period, the total deformation of the roof and floor of the roadway in a working face advance gradually increased from 1737 mm 80 m away from the working face to 2281 mm at the working face, and the total deformation of the two sidewalls gradually increased from 2094 mm 80 m away from the working face to 2211 mm at the working face. The damage to the roadway caused by secondary mining was much greater than that caused by the first mining. The collaborative control technology of long anchorage-top-cutting blasting stress relief is proposed to control the stability of the roadway. The engineering practice shows that the deformation of the roadway is effectively controlled under strong mining disturbance, and the maximum deformations of the roof, floor and sidewall are 17, 23, and 11 mm, respectively.

Opposition control is an effective active control strategy for drag reduction, which has been extensively investigated. In the current work, the essential characteristics of drag reduction by the blowing-only opposition control scheme (i.e., opposition blowing) in turbulent channel flow are investigated. It is demonstrated that, under the condition of constant wall-normal mass flux, the drag reduction achieved by the opposition blowing scheme is almost independent of the allocation of the blowing velocity among all the effective blowing points. This feature simplifies the complexity of the control scheme and provides great convenience for the application of the convolutional neural network (CNN) to implement the opposition blowing scheme, i.e., only the direction of the wall-normal velocity at the detection plane needs to be predicted. In this paper, both the streamwise and spanwise wall shear stresses are taken as the input of the CNN model, and the reasonability of the CNN model is verified from a statistical perspective. It is found that as long as the directions of the large wall-normal velocity fluctuations are accurately predicted, the opposition blowing scheme can be successfully implemented, in which the CNN model is able to ensure a high prediction accuracy. Furthermore, applying the trained network model to a flow at a higher Reynolds number than the training set can still accurately predict the directions of the large wall-normal velocity fluctuations, which generalizes the applicability of the CNN model.

Rock burst is a typical dynamic disaster in deep underground coal mining. Based on the support problems of the deep roadways in fully mechanized caving face 401111 of Hujiahe Coal Mine suffering from rock burst in Shaanxi Province of China, the failure law and influencing factors of the surrounding rock of the roadway are analyzed. The results show that the deformation of surrounding rock in the roadway shows the characteristics of elastic, plastic transformation, rheology, and expansion. At the same time, it has the typical characteristics of deep roadway, such as the fast deformation speed, long duration, asymmetric deformation, and large loose broken area of surrounding rock. Based on the principle of “strengthening support in shallow zones” and “deep pressure relief in deep zones” in the surrounding rock, the control scheme of surrounding rock in the return roadway of fully mechanized caving working face 401111 is proposed by taking the large diameter pressure relief and deep hole blasting as the main means of pressure relief. The practice shows that the surrounding rock of the return roadway is relatively stable after the implementation of the new scheme, which shows that the design of the new support scheme is reasonable and reliable. It is of great significance for the stability control of surrounding rock of the mining roadway suffering from rock burst.

This paper presents a novel method to attenuate large horizontal wind disturbance for a small-scale unmanned autonomous helicopter combining wind tunnel-based experimental data and a backstepping algorithm. Large horizontal wind disturbance is harmful to autonomous helicopters, especially to small ones because of their low inertia and the high cross-coupling effects among the multiple inputs. In order to achieve more accurate and faster attenuation of large wind disturbance, a new hybrid control architecture is proposed to take advantage of the direct force/moment compensation based on the wind tunnel experimental data. In this architecture, large horizontal wind disturbance is treated as an additional input to the control system instead of a small perturbation around the equilibrium state. A backstepping algorithm is then designed to guarantee the stable convergence of the helicopter to the desired position. The proposed technique is finally evaluated in simulation on the platform, HIROBO Eagle, compared with a traditional wind velocity compensation method.