Recently, sound-based diagnosis systems have been given much attention in many fields due to the advantages of their simple structure, non-touching measurement style, and low-power dissipation. In order to improve the efficiency of coal production and the safety of the coal mining process, accurate information is always essential. It is indicated that the sound signal produced during the cutting process of the coal mining shearer contains much cutting pattern identification information. In this paper, the original acoustic signal is first collected through an industrial microphone. To analyze the signal deeply, an adaptive Hilbert–Huang transform (HHT) was applied to decompose the sound to several intrinsic mode functions (IMFs) to subsequently acquire 1024 Hilbert marginal spectrum points. The 1024 time-frequency nodes were reorganized as a 32 × 32 feature map. Moreover, the LeNet-5 convolutional neural network (CNN), with three convolution layers and two sub-sampling layers, was used as the cutting pattern recognizer. A simulation example, with 10,000 training samples and 2000 testing samples, was conducted to prove the effectiveness of the proposed method. Finally, 1971 testing sound series were recognized accurately through the trained CNN and the proposed method achieved an identification rate of 98.55%.

This article takes a 120 W direct-drive permanent magnet synchronous generator (PMSG) for tidal current energy as the research object, with the aim of starting at low flow velocity, low voltage regulation, and high sealing performance. The research was conducted on the design method of the generator, and the parameter calculation formula is modified based on the structural characteristics of the generator. The design scheme is simulated using the finite element method, and the voltage regulation is optimized using evolutionary algorithm. A prototype was manufactured based on the optimized scheme, and drag experiments and sealing tests were conducted. After that, the generator and impeller were assembled, and water tank drag experiments were conducted. The experimental results verified the reliability of the motor design method in this paper.

Tidal energy, as a sustainable and environmentally friendly energy source, has attracted widespread attention in recent years. The technology of blade active pitch control is the key technology to cope with tidal velocity change and improve the stability and efficiency of horizontal-axis tidal generator sets. When solving the problem of speed variation, the core algorithm is the key to ensuring stable operation and improving the efficiency of power generation. When traditional PID is used to manage complex systems, the controller faces the challenge of complex parameter tuning and insufficient robustness. The application of a particle swarm optimization (PSO)–PID controller and fuzzy PID controller in the independent interval system of tidal generator sets is introduced for the first time in this paper. This paper presents a comparative study of unified pitch control and independent pitch control (using electric pitch control) for a three-rotor tidal generator with a rated capacity of 300 kw and a blade radius of 8.5 m. Simulation was carried out on the MATLAB/Simulink (2023a) platform to evaluate the performance of the two controllers under different flow rates and interference conditions. The results show that the PSO-PID controller has significant advantages in reducing overshoot, speeding up response times, and improving power generation efficiency. At the same time, the PSO-PID controller also shows superior performance in pitch angle adjustment frequency and generator output power and realizes timely and effective system stability control.

This research tackles the challenges of elevated parameter sensitivity and substantial model error in estimating the State of Charge (SOC) of lithium-ion batteries by introducing an Unscented Kalman filter (UKF) method that combines NDO optimisation with neural network-based online compensation. Initially, the state-space equations of the battery are formulated using a second-order RC equivalent circuit model, and the UKF is employed for preliminary State of Charge estimation. Secondly, the NDO algorithm is implemented to achieve global optimisation of the process noise Q and observation noise R in the UKF. To overcome the constraints of conventional single-error-metric methodologies, a weighted objective function is formulated, integrating the mean absolute error (MAE) and root mean square error (RMSE) of SOC estimation in a weighted ratio of 0.8MAE + 0.2RMSE, thus achieving a balance between overall accuracy and error stability. A single-hidden-layer feedforward neural network is developed and trained online utilising the backpropagation algorithm to dynamically address voltage prediction residuals. In comparison to conventional UKF and PSO-UKF approaches, the estimation error is markedly diminished, substantiating the efficacy and superiority of the suggested method in complicated operational scenarios.

Battery management systems depend on precise estimation of the battery’s state of charge. The accuracy and adaptability of estimation are limited by current approaches. An adaptive extended Kalman filter technique based on the moss growth optimization algorithm with wind intensity optimization is proposed to overcome these problems. The weight factor based on individual fitness and the number of iterations is combined to dynamically modify wind intensity to improve the moss growth optimization algorithm, which is then utilized to optimize the process noise covariance matrix in the Kalman filter. At the same time, the algorithm’s accuracy is enhanced by adaptively updating the measurement noise covariance matrix using the smoothing factor, which also prevents the filter from diverging and allows the algorithm to automatically update the noise parameters to better respond to changes in battery state and the influence of the external environment. Pulse current discharge experiments at various temperatures are used to confirm the efficacy of the improved algorithm proposed in this paper. The results demonstrate the superiority of the WOMGO-AEKF algorithm in terms of SOC estimate accuracy, since the root mean square error are much lower under various temperature circumstances than those of the conventional EKF algorithm.