圆度误差是轴类零件的重要几何参数，直接影响机械配合精度、产品性能及使用寿命。为进一步提升圆度误差评定的精度、效率和重复性，基于最小区域准则构建了圆度误差评定模型，同时为实现模型的高效求解，提出了一种基于改进帝企鹅算法的圆度误差快速精确评定方法。该方法引入自适应参数调整机制，增强帝企鹅算法在全局搜索与局部开发之间的动态平衡能力，同时采用差分进化策略，提高算法跳出局部最优解的能力。实验结果表明，改进后的帝企鹅算法在整体性能上优于原始算法，并且在圆度误差评定方面相较于遗传算法和单纯形算法有明显优势。从而，验证了在最小区域准则下进行圆度误差评定时该方法的可行性和有效性。

针对反向式行星滚柱丝杠副（Inverted Planetary Roller Screw Mechanism， IPRSM）弹性变形临界点轴向载荷难以精确求解的问题，本研究提出了一种基于Hertz接触理论和von Mises屈服准则的解析计算方法。通过分析IPRSM近载端滚柱-丝杠侧螺纹牙的应力应变特性，结合材料弹塑性本构关系，建立了弹性极限状态下临界轴向载荷的确定方法。研究基于Hertz接触理论对螺纹牙的接触几何学进行探究，对五种不同牙型角（70°-100°）IPRSM在不同承载范围内的力学性能进行了对比分析。研究结果表明：所提出的解析方法可有效预测近载端螺纹牙的临界载荷；在不同承载范围内，90°牙型角展现出最优的综合性能，其承载能力显著优于其他角度构型，可作为IPRSM牙型角的最佳设计参数。

针对滚动轴承运行退化呈现随机变点的多阶段特征,提出了一种新型的多阶段退化过程剩余寿命预测方法。首先,以离线历史数据估计各阶段模型的先验参数;其次,针对单一在线设备,通过贝叶斯变点检测方法进行变点的实时检测,采用贝叶斯更新方法在变点出现前对第1阶段参数进行更新,变点出现后对第2阶段进行更新;最后,利用多阶段模型进行剩余寿命预测。数值仿真和实例研究结果表明:基于贝叶斯变点检测的滚动轴承寿命预测方法可以提高85%的变点检测精度,进而实现高精度的多阶段剩余寿命预测。

针对目前睡眠分期中存在的依赖人工判别效率低、睡眠分期精度不高等问题，提出了一种基于改进粒子群优化算法优化支持向量机(IPSO-SVM)的睡眠分期模型，通过脑电(EEG)信号对睡眠过程进行准确分期。首先，对EEG信号进行滤波、分段等预处理；其次，提取EEG信号的时域、频域、非线性特征；最后，通过IPSO-SVM算法建立睡眠分期模型。该模型在PSO算法中引入模拟退火算法来提升算法的搜索能力，同时引入惯性权重自适应变异使粒子能够跳出局部最优解。使用ISRUC-Sleep数据集的前6位受试者数据对IPSO-SVM分类模型进行验证。结果表明：IPSO-SVM模型的平均睡眠分期准确率为92.34%,K系数为0.88,改进的睡眠分期模型具有较高的准确率和系统稳定性。

In the prediction of the remaining useful life (RUL) of rolling bearings, feature extraction and selection are critical prerequisites for accurate prediction, while the construction of the prediction model is the core. However, existing RUL prediction methods face two main challenges: (1) feature construction methods based on predefined indicators often ignore the correlation among features; and (2) single models typically yield limited prediction accuracy. To address these issues, this study proposes a feature selection method based on hierarchical clustering combined with the elbow method and a hybrid Transformer–GRU (Gated Recurrent Unit) model for RUL prediction. Specifically, the initially filtered feature set is further clustered using hierarchical clustering, and the optimal number of clusters is determined by the elbow method to construct a compact and representative feature set. This feature set is then input into a Transformer–GRU model, where the Transformer encoder captures temporal dependencies across time steps to generate rich feature representations, and the GRU network models their dynamic evolution over time to predict the bearing RUL. The proposed method is validated on the PHM2012 dataset. The experimental results show that after removing redundant features, the model’s training time is reduced by 8.61% and the number of parameters decreases by 23.26%. Compared with other benchmark models, the proposed Transformer–GRU model achieves a lower mean absolute error (MAE) of 0.0836 and a root mean square error (RMSE) of 0.1137, demonstrating superior predictive performance. These results confirm that the proposed feature selection method effectively eliminates feature redundancy, enhances training efficiency, and reduces model complexity, while the hybrid model significantly improves prediction accuracy. © 2025 by the authors.

The shape error of shaft-type mechanical components directly influences the quality, fitting precision and lifespan of the components. Among these, cylindricity error is a critical indicator for evaluating the precision of shaft-type components. Based on the new generation geometric product specifications & verification (GPS), this paper researched GPS inspection operation operators, determined extraction and fitting schemes, and constructed a mathematical model for cylindricity error evaluation. Consequently, a method for cylindricity error evaluation based on an improved whale optimization algorithm was proposed. The proposed algorithm introduced chaotic mapping and nonlinear parameters during population initialization to enhance solution quality. Subsequently, adaptive weighting coefficients were incorporated during spiral position updates to improve the algorithm's local search capability. Finally, Levy flight strategies were introduced during random search to enhance the algorithm's global search capability. This study conducted experimental validation and analysis by performing numerous comparative experiments on different extraction point numbers, cross-section numbers, evaluation criteria, and algorithms. The experimental results indicated that the proposed method for cylindricity error evaluation demonstrated significant improvements in both accuracy and efficiency compared to genetic algorithms, least squares methods, and others.

Roundness error is one of the core indicators for evaluating the geometric accuracy of round parts mechanical products, directly affecting product performance and service life. In the field of metrology, the accurate, rapid and standardized assessment of roundness error has always been a hot topic. This paper proposed a new method for evaluating roundness error based on improved bat algorithm. This method was based on the new geometric product specification for extraction, filtering and fitting. Based on the advantages of solving optimization problems using the bat algorithm, transformed the roundness error evaluation problem using the minimum zone method into a problem of using the bat algorithm to find the center of the minimum zone circle, then further solved for the roundness error value. Also, this algorithm effectively avoided falling into local optimal solutions by introducing chaotic inertia weights during the velocity update phase, it improved the accuracy and speed of the evaluation. Introduced adaptive parameters during the loudness and emission rate update phases to enhance the algorithm's global search capability, it enhanced the stability of the algorithm. The experimental results indicated, the efficiency of roundness error evaluation in the new method was significantly better than that of the genetic algorithm, the simplex algorithm and the emperor penguin algorithm. There was a significant improvement in evaluation accuracy and stability. The feasibility of this method in roundness error evaluation using the minimal zone method was validated.

Centrifugal pumps are important equipment in industrial production, and their safe and reliable operation is of great significance to water supply and industrial safety. During the use of centrifugal pumps, faults such as bearing damage, blade wear, shaft imbalance, shaft misalignment and water hammer often occur. Among them, although water hammer faults occur at a low frequency, they are difficult to monitor and pose significant risks to valve and pipeline interfaces. This article analyzes the causes, mechanisms and phenomena of water hammer faults in centrifugal pumps, designs a monitoring method to effectively monitor the vibration signal of the centrifugal pumps, extracts vibration characteristics to determine and record water hammer events, designs monitoring and diagnostic models for the edge layer and server side, and establishes an experimental verification testing system. The test results show that, under the conditions of simulating water hammer faults, after high-pass filtering of the collected vibration data, the kurtosis index, pulse index and margin index all exceed twice the threshold, and both sensors emit water hammer alarms. The designed data acquisition method can capture water hammer signals in a timely manner, and the analysis model can automatically identify water hammer faults based on existing fault knowledge and rules. This fully demonstrates the scientific and effective nature of the proposed centrifugal pump fault monitoring method and system, which is of great significance for ensuring the safe operation and improving the design of centrifugal pumps. © 2024 by the authors.

As modern production technology progresses, equipment complexity escalates, resulting in a rising failure rate. An intelligent remote monitoring and diagnosis system for equipment based on cloud-edge collaboration technology is designed to address the problems of poor data transmission ability and low fault diagnosis accuracy in traditional monitoring and diagnosis systems. The system realizes information perception, collection, and edge computing through edge intelligent devices. The feature extraction, pattern recognition, and intelligent information diagnosis are realized in the cloud platform, and the equipment's running state and diagnosis results are displayed in real time at the terminal. The research and design of this system are of great significance in reducing unexpected downtime of equipment and improving production efficiency. © Published under licence by IOP Publishing Ltd.

To solve the problem of "under-maintenance" and "over-maintenance" in the daily maintenance of equipment, the predictive maintenance method based on the running state of equipment has shown great advantages, and fault prediction is an important part of predictive maintenance. First, the spectrum information of the equipment is extracted by the Hilbert-full-vector spectrum as the input of fault prediction. Compared with the traditional spectrum, this spectrum information fuses the signals of two sensors in the same section of the device, which can reflect the actual operational state of the device more comprehensively. Then, the temporal convolutional network is used to predict the amplitudes of different feature frequencies, and the double-layer attention mechanism is introduced to mine the correlation between the corresponding amplitudes of different feature frequencies and between the data at different historical moments, to highlight the more important influencing factors. In this way, the prediction accuracy of the model for the amplitude corresponding to the feature frequency of concern is improved. Finally, experimental verification is carried out on the XJTU-SY dataset. The results show that the TCDAN model proposed in this paper is significantly superior to TCN, GRU, BiLSTM, and LSTM, which can provide a more effective decision-making basis for the predictive maintenance of equipment.