Explore the vast range of titles available.

Athlete engagement is influenced by several factors, including cohesion, passion and mental toughness. Machine learning methods are frequently employed to construct predictive models as a result of their high efficiency. In order to comprehend the effects of cohesion, passion and mental toughness on athlete engagement, this study utilizes the relevant methods of machine learning to construct a prediction model, so as to find the intrinsic connection between them. The construction and comparison methods of predictive models by machine learning algorithms are investigated to evaluate the level of predictive models in order to determine the optimal predictive model. The results show that the PSO-SVR model performs best in predicting athlete engagement, with a prediction accuracy of 0.9262, along with low RMSE (0.1227), MSE (0.0146) and MAE (0.0656). The prediction accuracy of the PSO-SVR model exhibits an obvious advantage. This advantage is mainly attributed to its strong generalization ability, nonlinear processing ability, and the ability to optimize and adapt to the feature space. Particularly noteworthy is that the PSO-SVR model reduces the RMSE (7.54%), MSE (17.05%), and MAE (3.53%) significantly, while improves the R 2 (1.69%), when compared to advanced algorithms such as SWO. These results indicate that the PSO-SVR model not only improves the accuracy of prediction, but also enhances the reliability of the model, making it a powerful tool for predicting athlete engagement. In summary, this study not only provides a new perspective for understanding athlete engagement, but also provides important practical guidance for improving athlete engagement and overall performance. By adopting the PSO-SVR model, we can more accurately identify and optimise the key factors affecting athlete engagement, thus bringing far-reaching implications for research and practice in sport science and related fields.

With the advancement of cognitive radar, applying deep neural networks to radar jamming recognition has become an indispensable research direction. However, as a common anti-jamming measure, the agility of radar waveform parameters degrades the effectiveness of jamming recognition, creating a trade-off between jamming recognition and anti-jamming agility. Specifically, for the same type of jamming, radar agility in frequency, pulse width, and bandwidth alters the profile and scale features of the jamming, posing challenges to conventional CNN-based jamming recognition. To address this challenge, this paper proposes an Adaptive Feature-Focusing CNN (AFF-CNN). A pre-trained AFF module is designed to establish a mapping between agile parameters and adaptive feature scales. Operating on time-domain high-resolution range profiles (HRRP) and time–frequency domain short-time Fourier transform (STFT) data, this module calibrates deviations induced by radar inter-pulse parameter agility and enhances the capability of salient signal feature-focusing. Furthermore, a lightweight 1D-2D feature fusion CNN is designed to process these adaptive features and recognize jamming using single-pulse signals, thereby enhancing the network’s adaptability to inter-pulse parameter agility in radar systems. Simulation results demonstrate superior recognition accuracy and generalization capability compared to five comparative approaches, confirming effective adaptation to inter-pulse agility scenarios.

In order to investigate the internal flow characteristics and hydraulic stability of vertical submersible pump station in forward and reverse operation, the steady and unsteady three-dimensional numerical simulation of vertical submersible axial-flow pump device was carried out based on CFD and the energy performance of the pump device was predicted. In this paper, the internal flow characteristics of the vertical submersible axial-flow pump device under forward and reverse operation were analyzed, and the optimization of the structure passed by water was carried out to improve the efficiency of the pump device in forward and reverse operation. The results show that the performance of the pump device is good when it is running in the forward direction, the peak efficiency of the pump device is 72.22% and the corresponding head is 4.01 m. When it is running in the reverse direction, the performance of the pump device decreases significantly with the peak efficiency is only 36.03% and the corresponding head is 3.34 m. The hydraulic loss in the dust-pan-shaped conduit is very small in the forward operation, the wellbore conduit is the main factor which affects the efficiency of the submersible axial flow pump device, the loss ratio is 12%–44%. When the pump device is in reverse operation, the hydraulic loss is similar but the hydraulic performance is poor and the hydraulic loss is obviously larger than that in forward operation. A guide plate is added to the dust-pan-shaped conduit at 0.27D (D is the nominal diameter of impeller) along the axis direction of the conduit, and a elbow flow conduit with the corner radius R of 0.83D is selected to replace the wellbore conduit, the bad flow state disappeared and the efficiency of the pump device increased by 5.19% in the forward operation while the efficiency of the pump device increased by 9.62% in the reverse operation.

The energy loss of the vertical axial flow pump device increases due to the unstable internal flow, which reduces the efficiency of the pump device and increases its energy consumption of the pump device. The research results of the flow loss characteristics of the total internal conduit are still unclear. Therefore, to show the internal energy loss mechanism of the axial flow pump, this paper used the entropy production method to calculate the energy loss of the total conduit of the pump device to clarify the internal energy loss mechanism of the pump device. The results show that the energy loss of the impeller is the largest under various flow conditions, accounting for more than 40% of the total energy loss of the pump device. The variation trend of the volume average entropy production and the energy loss is similar under various flow coefficients (KQ). The volume average entropy production rate (EPR) and the energy loss decrease first and then increase with the increase of flow, the minimum volume average entropy production is 378,000 W/m3 at KQ = 0.52, and the area average EPR of the impeller increases gradually with the increase of flow. Under various flow coefficient KQ, the energy loss of campaniform inlet conduit is the smallest, accounting for less than 1% of the total energy loss. Its maximum value is 63.58 W. The energy loss of the guide vane and elbow increases with the increase of flow coefficient KQ, and the maximum ratio of energy loss to the total energy loss of the pump device is 29% and 21%, respectively, at small flow condition KQ = 0.38. The energy loss of straight outlet conduit reduces first and then increases with the increase of flow coefficient KQ. When flow coefficient KQ = 0.62, it accounts for 27% of the total energy loss of the pump device, but its area average entropy production rate (EPR) and volume average entropy production rate (EPR) are small. The main entropy production loss in the pump device is dominated by entropy production by turbulent dissipation (EPTD), and the proportion of entropy production by direct dissipation (EPDD) is the smallest.

Change detection using synthetic aperture radar (SAR) multi-temporal images only detects the change area and generates no information such as change type, which limits its development. This study proposed a new unsupervised application of SAR images that can recognize the change type of the area. First, a regionally restricted principal component analysis k-mean (RRPCA-Kmean) clustering algorithm, combining principal component analysis, k-mean clustering, and mathematical morphology composition, was designed to obtain pre-classification results in combination with change type vectors. Second, a lightweight MobileNet was designed based on the results of the first stage to perform the reclassification of the pre-classification results and obtain the change recognition results of the changed regions. The experimental results using SAR datasets with different resolutions show that the method can guarantee change recognition results with good change detection correctness.

In this paper, a single-equation drift-flux type model for gas-lead-bismuth eutectic (LBE) two-phase flow analysis in the LBE fast reactor steam generator tube rupture (SGTR) accident is established. As the area-averaged superficial gas velocity increases, the calculated exponent P in the Bankoff model increases, and the distribution parameter C 0 decreases. The reliability of the model is confirmed by comparing the predicted results with a total of 76 sets of open experimental data from a bubble-column case and a gas lift pump case. The relative deviation between the predicted and experimental values of the void fraction is within 20 %. The model proposed in this paper helps to realize the early warning and analysis of SGTR accidents in LBE fast reactors, and can provide theoretical and technical guidance for the safety design and evaluation of LBE fast reactors.

Large hospitals can be complex, with numerous discipline and subspecialty settings. Patients may have limited medical knowledge, making it difficult for them to determine which department to visit. As a result, visits to the wrong departments and unnecessary appointments are common. To address this issue, modern hospitals require a remote system capable of performing intelligent triage, enabling patients to perform self-service triage. To address the challenges outlined above, this study presents an intelligent triage system based on transfer learning, capable of processing multilabel neurological medical texts. The system predicts a diagnosis and corresponding department based on the patient’s input. It utilizes the triage priority (TP) method to label diagnostic combinations found in medical records, converting a multilabel problem into a single-label one. The system considers disease severity and reduces the “class overlapping” of the dataset. The BERT model classifies the chief complaint text, predicting a primary diagnosis corresponding to the complaint. To address data imbalance, a composite loss function based on cost-sensitive learning is added to the BERT architecture. The study results indicate that the TP method achieves a classification accuracy of 87.47% on medical record text, outperforming other problem transformation methods. By incorporating the composite loss function, the system’s accuracy rate improves to 88.38% surpassing other loss functions. Compared to traditional methods, this system does not introduce significant complexity, yet substantially improves triage accuracy, reduces patient input confusion, and enhances hospital triage capabilities, ultimately improving the patient’s medical experience. The findings could provide a reference for intelligent triage development.

In this paper, the motion of a water vapor bubble rising in molten lead-bismuth eutectic (LBE) was simulated. The force state of the bubbles before and during the rising process was discussed, explaining the mechanism of bubble deformation and development. The rising terminal velocities of 8 mm, 10 mm and 12 mm bubbles at 200 °C calculated by VOF model were approximately 0.20 m/s, 0.22 m/s and 0.23 m/s, respectively. Combined with the results of numerical calculations, the terminal velocities of the bubble were corrected using three drag force models. It was found that the corrected terminal velocity of the bubbles increases with an increase in the bubble diameter. Further, the acoustic radiation phenomenon during bubble rising was discussed. The study provides theoretical guidance for accident process analysis of steam generator tube rupture (SGTR) in advanced nuclear systems.

The shaft tubular pump device is widely used in various water diversion projects because of its ultra-low head and large flow characteristics. Due to the tip clearance between the blade and the shroud, it is easy to cause hydraulic mechanical performance changes, induced vibration, and noise, which seriously affects the safe and stable operation of the pump. Steady and unsteady three-dimensional flow field numerical simulations of a shaft tubular pump device were carried out using computational fluid dynamics to investigate the impeller flow properties of the device under various flow conditions, including the tip clearance leakage flow (TCLF) and change rule of pressure pulsation. The TCLF, vortex morphology evolution, and pressure pulsation properties of the impeller tip clearance were analyzed. The results show that with an increase in the flow rate, the influence of the tip clearance size on the tip clearance flow decreases, the TCLF decreases, and the axial velocity of the water flow at the tip clearance increases. When the flow rate increases, the swirling strength of the tip leakage vortex decreases, and the distance between the tip leakage vortex and the suction surface of the blade increases. With the increase in flow rate, the pressure pulsation amplitude at the tip clearance increases first and then decreases. The focus of this study is to analyze the variation of tip clearance flow field and pressure pulsation under multiple working conditions, aiming to provide some help for improving the performance of the pump device and ensuring its safe operation.

The unsteady three‐dimensional numerical simulation calculation of the vertical axial flow pump device is performed based on CFD to examine the pressure pulsation and energy distribution features of the water flow within the siphon outlet conduit (SOC) under the hydraulic coupling of the pump and the flow conduit. The pressure pulsation signals (PPS) of monitoring points are decomposed using the Hilbert–Huang approach via empirical mode decomposition (EMD) and Hilbert spectrum analysis. The results show that the PPS of monitoring points of the SOC has no obvious periodicity. The low‐frequency range below 20 Hz serves as the primary frequency, and the energy ratio of the high‐frequency signal above 700 Hz is less than 1%. Under the condition of a small flow rate 0.3Qbep, there is obvious high‐frequency pulsation above 500 Hz at the inlet of the upstream section of the SOC, and there are periodic components distributed around 200 Hz. The energy of the pressure pulsation is primarily focused in the low‐frequency range below 40 Hz at the SOC outlet section. The PPS at the top and bottom monitoring points of the hump section are consistent, and the pressure pulsation energy (PPE) is mainly concentrated in the low frequency below 40 Hz. In both the big flow condition (1.2Qbep) and the optimal flow condition (1.0Qbep), the PPE of the monitoring points at the top of the hump section is distributed in the middle and low‐frequency band below 40 Hz, and the energy of monitoring points at the bottom of the hump section is concentrated in the low‐frequency band below 20 Hz, accounting for more than 70%. When the flow rate increases from 0.3Qbep to 1.2Qbep, the peak value of the pressure pulsation coefficient at the main frequency of each monitoring point at the top of the hump section changes little, and the peak value of the pressure pulsation coefficient at the main frequency of each monitoring point at the bottom increases first and then decreases. From the upstream section to the hump section of the SOC, the average frequency of each intrinsic mode function (IMF) of the PPS under different flow conditions shows an overall increasing trend. From the hump section of the SOC to its outlet, the average frequency of each IMF of the PPS decreases under the conditions of 1.0Qbep and 1.2Qbep, and there is no obvious change under the condition of 0.3Qbep. The unsteady three‐dimensional numerical simulation calculation of the vertical axial flow pump device is performed based on CFD to examine the pressure pulsation and energy distribution features of the water flow in the siphon outlet conduit under the hydraulic coupling of the pump and the flow conduit. The pressure pulsation signals of monitoring points are decomposed using the Hilbert–Huang approach via empirical mode decompostiton (EMD) and Hilbert spectrum analysis.