The standard support vector machine (SVM) performs poorly on the identification problem of low velocity impact areas due to its lower accuracy rate. Improving SVM's performance using the bat algorithm (BA) is feasible, but BA has the premature convergence problem. In this study, a hybrid bat algorithm with double mutation operations (DMBA), in which the Cauchy mutation operator and the extremal optimization mutation operator are integrated into BA, is proposed to enhance BA's ability to jump out of the local optima. Then, a novel SVM based on this hybrid BA, which is called SVM_DMBA, is developed to address the identification problem. Compared with the standard SVM and twelve improved SVM methods which are combined with the standard algorithms, advanced algorithms, and bat variants, the significant performance of SVM_DMBA is validated using UCI datasets. Moreover, to identify low velocity impact areas, SVM_DMBA is applied to the low velocity impact localization system based on fiber Bragg grating (FBG) sensors. The statistical results indicate that SVM_DMBA is a significantly effective method for identifying the low velocity impact areas and generates higher identification accuracy than comparative methods. For 64 low velocity impact areas of 30 mm × 30 mm on an aluminium plate, the average identification error obtained by SVM_DMBA is 1.615%.

Marine riser is a key equipment in offshore drilling operation, and failure of the riser can lead to drilling moratorium; in severe cases, it may cause oil and gas leaks. In this paper, the time-dependent boundary conditions of the riser and the randomness of wave load are considered to improve the calculation efficiency and accuracy of the dynamic response of the jack-up riser. Based on the Euler–Bernoulli beam theory, an analytical method to determine the response of the jack-up riser subjected to the random wave load was established by the Mindlin–Goodman method in the frequency domain, and an experiment was carried out to verify it. The research shows that transverse dynamic response is the main component of the transverse response of the riser, and the method proposed is feasible to calculate the transverse response of the riser.

Microbubble cleaning technology has the characteristics of environmental protection and low energy consumption and has been initially applied in the field of oil sludge cleaning. For the controllability of microbubbles in the cleaning process, this paper adopted the numerical simulation method to quantitatively study the growth and collapse mechanism of bubbles in the cleaning process, the influence law of flow field, and parameter changes on the dynamic behavior of bubbles from the perspective of micro-dynamics. It was found that the dynamic characteristics of the flow field around the bubble in the free field show a symmetrical distribution, while the motion of the fluid near the wall is blocked by the wall, and the flow field between the bubble and the wall becomes irregular. It was also found that the large amplitude pressure changes in microbubbles produced a “plastic hinge” alternating impact on the wall, the bubble collapse, and wall pulsation pressure change are mainly controlled by the driving pressure. The liquid temperature mainly affects the dynamic characteristics of the bubble by causing a change in the viscosity of the medium. Under the condition of P_d = 0.1 MPa and γ = 1.5, when the liquid viscosity decreases from 0.110 to 0.00314 Pa·s, the maximum pressure affected by the first bubble collapse increases from 200.71 to 317.74 Kpa. Compared with the bubble distribution, the impact of increasing the number of bubbles on the wall is more significant. Under the condition of γ = 1 and P_d = 0.1 MPa, compared with the single bubble, the pulse pressure of nine bubbles’ collapse on the wall increases by 100 KPa. The research results can provide technical support for the development of microbubble cleaning technology.