Long series time forecasting has become a popular research direction in recent years, due to the ability to predict weather changes, traffic conditions and so on. This paper provides a comprehensive discussion of long series time forecasting techniques and their applications, using the Informer algorithm model as a framework. Specifically, we examine sequential time prediction models published in the last two years, including the tightly coupled convolutional transformer (TCCT) algorithm, Autoformer algorithm, FEDformer algorithm, Pyraformer algorithm, and Triformer algorithm. Researchers have made significant improvements to the attention mechanism and Informer algorithm model architecture in these different neural network models, resulting in recent approaches such as wavelet enhancement structure, auto-correlation mechanism, and depth decomposition architecture. In addition to the above, attention algorithms and many models show potential and possibility in mechanical vibration prediction. In recent state-of-the-art studies, researchers have used the Informer algorithm model as an experimental control, and it can be seen that the algorithm model itself has research value. The informer algorithm model performs relatively well on various data sets and has become a more typical algorithm model for time series forecasting, and its model value is worthy of in-depth exploration and research. This paper discusses the structures and innovations of five representative models, including Informer, and reviews the performance of different neural network structures. The advantages and disadvantages of each model are discussed and compared, and finally, the future research direction of long series time forecasting is discussed.

This paper presents a comprehensive state-of-the-art review of magnetic negative stiffness (MNS) devices in the realm of vibration isolation systems, spanning from foundational theoretical models to practical engineering applications. The emergence of MNS technology represents a significant advancement in the field of vibration isolation, introducing a method capable of achieving near-zero stiffness to effectively attenuate low-frequency vibration. Through a systematic exploration of the evolution of vibration isolation methodologies—encompassing passive, active, and hybrid techniques—this article elucidates the underlying principles of quasi-zero stiffness (QZS) and investigates various configurations of MNS isolators, such as the linear spring, bending beam, level spring-link, and cam-roller designs. Our comprehensive analysis extends to the optimization and application of these isolators across diverse engineering domains, highlighting their pivotal role in enhancing the isolation efficiency against low-frequency vibrations. By integrating experimental validations with theoretical insights, this study underscores the transformative potential of MNS devices in redefining vibration isolation capabilities, particularly in expanding the isolation frequency band while preserving the load-bearing capacities. As the authors of this review, not only are the current advancements within MNS device research cataloged but also future trajectories are projected, advocating for continued innovation and tailored designs to fully exploit the advantages of MNS technology in specialized vibration isolation scenarios.

Due to the three-dimensional non-axisymmetric shape of the volute, its interaction with the impeller increases the internal flow field complexity and instability of the marine centrifugal pump, representing the main reason for pump body vibration and hydraulic noise. First, the basic principle of fluid machinery noise calculation was explained based on the Lighthill acoustic analogy method and Curle’s theory. Then, the fluid pressure pulsation and flow characteristics of centrifugal pumps were analyzed using the Fluent software, after which the Actran software was used to examine the flow-induced vibration noise properties. The results showed that the clearance size significantly impacted the pump head, while the peak value of the flow-induced vibration response was mainly twice the blade frequency. Although a larger ring clearance increased the structural vibration, it had little impact on the sound pressure level changes in the external sound field. The results provided a new method for the structural optimization and low-noise design of marine centrifugal pumps.

With the rapid development of precision instruments, aerospace, and automotive industries, the demand for compact vibration isolators capable of suppressing low-frequency vibrations has surged. Although prior reviews have established the theoretical framework of quasi-zero stiffness (QZS) isolators, critical gaps persist in addressing their compact design under strong nonlinear dynamics and diverse engineering constraints. This review systematically analyzes the dynamic characteristics of QZS systems under nonlinear effects and evaluates five innovative design methodologies for compact QZS isolators: special spring type, magnetic type, bionic type, metamaterials-based type, and origami-inspired type. Key findings reveal that special spring-type isolators are simple to design and space-efficient but difficult to machine. Magnetic-type isolators achieve ultra-low start-up frequencies but face thermal instability. Metamaterial designs enable multifunctional integration at the cost of manufacturing complexity, while bionic-inspired and origami-inspired isolators are difficult to abstract for practical applications. We find that current research tends to prioritize miniaturization over the synergistic optimization of load capacity, broadband isolation, and adaptability. Future research should focus on multi-degree-of-freedom systems, coupled metamaterials-bionic structures, and active magnetic control. This work provides a key roadmap for advancing compact QZS technology in space-constrained applications.