Lei Zhang

The ship power equipment serves as a critical energy source for shipping. However, it commonly encounter intricate challenges related to vibrations. These vibrations not only pose risks of structural damage but also contribute to energy dissipation. Consequently, this study introduces a double-layer, multi-degree-of-freedom active vibration isolation system containing a raft. The system’s active actuators, tubular motors, are capable of both generating active forces to mitigate vibrations and harvesting vibration energy through electromagnetic induction. Mathematical models for the output force and energy feeding of the tubular motor are established by fitting experimental data. Furthermore, this paper presents designs for both model predictive control (MPC) active vibration isolation systems and linear quadratic regulator vibration isolation system, comparing their vibration isolation performance against that of traditional passive vibration isolation systems. Additionally, the crested porcupine algorithm is employed to optimize the control parameters of the MPC system, further enhancing its vibration isolation performance. To address variable vibration excitations, this paper also proposes a switching control strategy that enables the vibration isolation system to switch between active control and passive energy feedback work modes. This allows the system to harvest vibration energy when subjected to small excitations and to perform active control when subjected to large excitations.

Active vibration isolation systems are essential for the reliability of high-precision marine and deep-sea equipment, in which electromagnetic actuators are widely adopted for achieving fast response and high efficiency. However, permanent magnet synchronous linear motors (PMSLMs) face a critical trade-off between vibration suppression and thermal safety during long-term operation. To address this challenge, this paper presents an in-house designed PMSLM and proposes an integrated framework that synergizes multi-objective structural optimization with an adaptive reinforcement learning-based model predictive control (RL-MPC) strategy. First, a multi-objective optimization approach is developed by integrating Taguchi orthogonal experiments, the Box–Behnken response surface methodology, and a novel dream optimization algorithm (DOA) to enhance the electromagnetic performance of the motor. Compared with the conventional NSGA-II algorithm, the dream sharing and forgetting mechanism in DOA enables it to effectively escape from local optimal solutions. Simulation results demonstrate a 22.74% increase in average thrust and a 78.81% reduction in thrust ripple, alongside significant improvements in thermal safety. Based on the high-performance motor, this paper proposes an adaptive RL-MPC strategy with proximal policy optimization algorithm. During the offline training phase, the agent iteratively interacts with the data-driven thermal reduced-order model to learn an optimal control strategy. After training, the agent enables the MPC controller to autonomously adapt its weighting matrix for varying thermal conditions during online operation. Simulation results show that the RL-MPC controller effectively maintains the motor temperature within safe limits while achieving superior vibration isolation performance. Ultimately, this study provides a robust technical foundation for the long-term, reliable operation of high-performance active vibration isolation systems in complex marine environments.

In vibration isolation systems, a large amount of vibration energy is usually lost as heat, which results in a significant loss of potentially recovered energy. This work suggests a self-powered hybrid electronic interface circuit for vibration energy recovery to overcome the drawbacks of traditional piezoelectric energy harvesting, such as low output power, strong load dependence, and inadequate multi-source harvesting capabilities. The suggested circuit combines synchronized electric charge extraction (SECE) and parallel synchronized switch harvesting on inductor (P-SSHI), taking advantage of their complementary features: SECE shows weak load dependence but relatively low power output, while P-SSHI offers relatively high output power but suffers from load sensitivity. To further enhance the output performance and operational robustness, the exponential-trigonometric optimization (ETO) algorithm is employed to globally optimize key circuit parameters, including inductance and storage capacitance. In addition, a multi-transducers energy harvesting strategy is developed to enable simultaneous energy extraction from multiple piezoelectric transducers, improving the wideband harvesting capability under practical vibration conditions. The experimental findings indicate that the suggested hybrid circuit exhibits significant output power while maintaining minimal load dependence. The maximum output power of the proposed circuit is 3.3 times higher than the traditional standard energy harvesting (SEH) circuit.

With the development of cutting‐edge technologies, vehicle energy optimization is embracing new development opportunities. In this study, a joint optimization strategy utilizing the model predictive control (MPC) and crested porcupine optimizer (CPO) is proposed for the speed planning and energy management of fuel cell hybrid electric vehicles (FCHEVs) in multi‐signal road segments. In the context of Vehicle‐to‐Infrastructure communication, vehicle speed planning is merged with MPC. A multi‐objective convex cost function is formulated based on the reference vehicle speed, and the weight coefficients in the cost function are adjusted through the CPO. Subsequently, the optimal vehicle speed trajectory is produced by using MPC. Simultaneously, MPC is also utilized to address energy management issues. When formulating the energy management objective function, the consumption of hydrogen and the loss of fuel cell (FC) life are considered to enhance the system's economic efficiency. CPO is also employed to optimize the weight coefficients in the cost function. Simulation results for the scenario of six traffic lights indicate that the energy management strategy proposed in this study, based on MPC, reduces hydrogen consumption by 5.7% compared to the traditional Pontryagin's Minimum Principle (PMP), and the output power fluctuation of the FC is minor.

In this study, the optimization of construction machinery scheduling within roadbed construction projects is explored, taking into account both personnel fatigue and sequence-dependent setup times. A sophisticated optimization model has been developed to simulate the optimal operation of machinery, aiming to maximize equipment utilization efficiency while addressing the challenges posed by worker fatigue. An innovative algorithm, the improved hybrid gray wolf and whale algorithm fused with a penalty function for construction machinery optimization (IHWGWO), is introduced, incorporating a penalty function to handle constraints effectively. This algorithm reduces the number of iterations required for optimization and, subsequently, cuts down on energy consumption. Through rigorous analysis and comparison with existing algorithms, the proposed IHWGWO demonstrates a significant reduction in both iteration count and financial expenditure. Simulation outcomes confirm the accuracy and practicality of the model and algorithm, establishing a promising new approach for scheduling in construction engineering.

Optimization scheduling plays a pivotal role in construction projects, significantly influencing both the overall project schedule and its efficiency. This study focuses on optimizing the scheduling of electric highway engineering projects within roadbed construction. The research considers multiple earthmoving processes and optimizes the working time of each piece of equipment, taking into account its capacity and speed within a limited working week. The study is further contextualized by the use of regional time‐of‐use (TOU) electricity pricing. A sophisticated optimization model is developed to simulate optimal machinery operation, striking a balance between energy consumption and work efficiency. This paper introduces an innovative algorithm, the improved crested porcupine optimizer (ICPO), which incorporates Latin hypercube sampling for population initialization. To enhance algorithmic effectiveness, a combined strategy of parallel and compact processing is employed. This approach reduces the number of iterations required for optimization and consequently lowers energy consumption. Rigorous analysis and comparison with existing algorithms demonstrate that ICPO significantly reduces both iteration count and financial expenditure. Simulation results validate the accuracy and practicality of the proposed model and algorithm, showing a reduction of over 7% in both engineering time and energy consumption.

In real-world industrial applications, bearings are typically operated under variable speeds and loads depending on the production condition, which results in nonstationary vibration signals from the bearings. Synchrosqueezing transform is a method that can effectively reflect the change in frequency with time, which is suitable for processing nonstationary bearing signals. However, significant classification features are difficult to extract from time–frequency information when operation conditions such as speed and load change frequently. Hence, an improved two-dimensional (2D) convolutional neural network (CNN) named the 2D multiscale cascade CNN (2D MC-CNN) is proposed for performing bearing fault diagnosis under various operating conditions. In a 2D MC-CNN, a multiscale information fusion layer is added prior to the convolutional layer of a conventional CNN to form MC images such that sensitive bands can be acquired for fault recognition. Experiments are conducted on bearings by considering various sets of fault categories and fault severity levels under six operating conditions. The experimental results show that the proposed method effectively extracts fault-related features and demonstrates excellent diagnostic accuracy and robustness. Comparisons with the original CNN and other typically used fault diagnosis methods based on the same dataset demonstrate the effectiveness of the proposed 2D MC-CNN and bearing fault diagnosis method.