作者:
Wu, MingmingWuhu Univ
Sch Automot Engn & Intelligent Mfg Wuhu 241000 Peoples R China
The goal of management optimization scheduling in manufacturing plants is to improve machining efficiency and reduce costs, which is one of the research hotspots in the current era. The study proposed a particleswarm...
详细信息
The goal of management optimization scheduling in manufacturing plants is to improve machining efficiency and reduce costs, which is one of the research hotspots in the current era. The study proposed a particle swarm optimization algorithm incorporating the frog-leaping algorithm, which combined the grouping mechanism with the global search to improve the search speed of the algorithm, and also incorporated the mutation and crossover ideas of the genetic algorithm. To enhance the machining efficiency while minimizing time and resource requirements, two buffering mechanisms were used for the machining process in this algorithm. The algorithm ultimately achieved the optimal solution of 1170 around the 10th generation, according to experiments, which reduced the maximum machining time by 22%, the average production cycle time by 23%, the machine utilization rate reached 69%, and the percentage of the optimal relative error was almost less than 4%. Additionally, the algorithm's average relative error fluctuation is less than that of the other algorithms, indicating that this algorithm is more stable. This result shows that the particle swarm optimization algorithm incorporating the frog hopping algorithm in this study has good practical value in optimizing the scheduling of production management in manufacturing workshops for improving the processing efficiency and reducing the cost, which is beneficial to the development of the manufacturing industry.
Most of the studies on multimode vibration reduction of floating raft systems remain at the stage of theoretical analysis, while relevant experimental studies are rare. In this paper, an experimental setup for a scale...
详细信息
Most of the studies on multimode vibration reduction of floating raft systems remain at the stage of theoretical analysis, while relevant experimental studies are rare. In this paper, an experimental setup for a scaled-down floating raft system is constructed. The vertical track nonlinear energy sink (TNES) cells are experimentally applied for the first time to suppress the multimode vibration of the floating raft system. To ensure the damping effect is not affected by additional mass, the TNES cells are always installed on the floating raft system. The TNES is able to achieve vibration suppression by allowing unrestricted movement of its vibrator. Two damping systems with different TNESs placement are proposed. Experimental modal analysis is performed on the floating raft structure to determine its response characteristics. Based on the results, different magnitudes of excitation force are applied to each order mode to effectively suppress the multimode vibration of the system. Meanwhile, the nonlinear system coupled with TNES cells is analyzed using the harmonic balance method (HBM) to obtain the approximate analytical solution. The system responses obtained from the analytical solution are compared with the experimental data results. The particleswarmoptimization (PSO) algorithm is used to obtain the optimal parameters of the TNESs for vibration suppression. The results show that the multimodal vibration of the floating raft structure is effectively suppressed by the TNES cells in both experimental and theoretical analyses. The vibration suppression effect for all modes is significantly improved by the PSO algorithm. In conclusion, the research content of this paper provides a practical and feasible vibration suppression solution for the design of floating raft systems.
PurposeThis study aims to enhance the prediction accuracy of hydroelectricity consumption in China, with a focus on addressing the challenges posed by complex and nonlinear characteristics of the data. A novel grey mu...
详细信息
PurposeThis study aims to enhance the prediction accuracy of hydroelectricity consumption in China, with a focus on addressing the challenges posed by complex and nonlinear characteristics of the data. A novel grey multivariate prediction model with structural optimization is proposed to overcome the limitations of existing grey forecasting ***/methodology/approachThis paper innovatively introduces fractional order and nonlinear parameter terms to develop a novel fractional multivariate grey prediction model based on the NSGM(1, N) model. The particle swarm optimization algorithm is then utilized to compute the model's hyperparameters. Subsequently, the proposed model is applied to forecast China's hydroelectricity consumption and is compared with other models for *** derivation results demonstrate that the new model has good compatibility. Empirical results indicate that the FMGM(1, N, a) model outperforms other models in predicting the hydroelectricity consumption of China. This demonstrates the model's effectiveness in handling complex and nonlinear data, emphasizing its practical *** implicationsThis paper introduces a scientific and efficient method for forecasting hydroelectricity consumption in China, particularly when confronted with complexity and nonlinearity. The predicted results can provide a solid support for China's hydroelectricity resource development scheduling and ***/valueThe primary contribution of this paper is to propose a novel fractional multivariate grey prediction model that can handle nonlinear and complex series more effectively.
Accurately predicting oil well production volume is of great significance in oilfield production. To overcome the shortcomings in the current study of oil well production prediction, we propose a hybrid model (GRU-KAN...
详细信息
Accurately predicting oil well production volume is of great significance in oilfield production. To overcome the shortcomings in the current study of oil well production prediction, we propose a hybrid model (GRU-KAN) with the gated recurrent unit (GRU) and Kolmogorov-Arnold network (KAN). The GRU-KAN model utilizes GRU to extract temporal features and KAN to capture complex nonlinear relationships. First, the MissForest algorithm is employed to handle anomalous data, improving data quality. The Pearson correlation coefficient is used to select the most significant features. These selected features are used as input to the GRU-KAN model to establish the oil well production prediction model. Then, the particleswarmoptimization (PSO) algorithm is used to enhance the predictive performance. Finally, the model is evaluated on the test set. The validity of the model was verified on two oil wells and the results on well F14 show that the proposed GRU-KAN model achieves a Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2) values of 11.90, 9.18, 6.0% and 0.95, respectively. Compared to popular single and hybrid models, the GRU-KAN model achieves higher production-prediction accuracy and higher computational efficiency. The model can be applied to the formulation of oilfield-development plans, which is of great theoretical and practical significance to the advancement of oilfield technology levels.
The plastic stress distribution (PSD) method is used as the primary method in typical design codes for calculating the strength of concrete-filled steel tubular (CFST) members. However, the PSD method can only be appl...
详细信息
The plastic stress distribution (PSD) method is used as the primary method in typical design codes for calculating the strength of concrete-filled steel tubular (CFST) members. However, the PSD method can only be applied to members with limited ranges of material strengths and cross-sectional slenderness ratios, and the calculation methods are lacking or relatively complicated for members beyond the limitations. In this work, an improved PSD method is proposed for the strength prediction of CFST members with different cross-sectional slenderness ratios and material strengths, by using the concrete strength factor fi1 to consider the possible compressive strength increase or reduction of the concrete due to the confinement or local buckling from the steel tube and the steel strength factor fi2 to consider the potential compressive strength reduction of the steel tube due to local buckling. The direct inverse analysis using the improved particle swarm optimization algorithm is then conducted to identify the strength factors fi1 and fi2 based on the extensive experimental results. Machine learning algorithms are finally explored to train the rules between the strength factors (fi1 and fi2) and the member properties including the diameter or width and depth, wall thickness, and material strength, and the predicted results are in good agreement with the experimental results. These results further specify the accurate plastic stress distribution, and provide a strong justification for possible changes to the design codes to expand the use of the PSD method to all types of CFST members.
This paper presents an adaptive dynamic surface control (DSC) method for nonlinear systems with multiple disturbances, parameter uncertainties, and unknown nonlinear dynamics, using a reduced-order extended state obse...
详细信息
This paper presents an adaptive dynamic surface control (DSC) method for nonlinear systems with multiple disturbances, parameter uncertainties, and unknown nonlinear dynamics, using a reduced-order extended state observer (ROESO). Compared to related methods, this proposed approach offers several distinct advantages: (i) The method does not require knowledge of the upper bound function for unknown nonlinear dynamics, allowing the controlled plant to not be bounded-input bounded-state, thus expanding the applicability of the DSC method;(ii) By utilizing known model information, an ROESO is designed to handle mismatched uncertainties and disturbances, reducing the load on the observer and enhancing its capability to suppress unknown nonlinear dynamics;(iii) This method employs an adaptive output-feedback DSC approach, which is more practical and easier to implement than state-feedback methods;and (iv) The observer gain, adaptive gain, and DSC gain are simultaneously optimized using a particle swarm optimization algorithm. Additionally, detailed stability analysis is provided, and simulations and comparative experiments are conducted on a rotational system to demonstrate the efficacy and superiority of the proposed method.
Watermarking is a technique used to address issues related to the widespread use of the internet, such as copyright protection, tamper localization, and authentication. However, most watermarking approaches negatively...
详细信息
Watermarking is a technique used to address issues related to the widespread use of the internet, such as copyright protection, tamper localization, and authentication. However, most watermarking approaches negatively affect the quality of the original image. In this research, we propose an optimized image watermarking approach that utilizes the dual-tree complex wavelet transform and particle swarm optimization algorithm. Our approach focuses on maintaining the highest possible quality of the watermarked image by minimizing any noticeable changes. During the embedding phase, we break down the original image using a technique called dual-tree complex wavelet transform (DTCWT) and then use particleswarmoptimization (PSO) to choose specific coefficients. We embed the bits of a binary logo into the least significant bits of these selected coefficients, creating the watermarked image. To extract the watermark, we reverse the embedding process by first decomposing both versions of the input image using DTCWT and extracting the same coefficients to retrieve those corresponding bits (watermark). In our experiments, we used a common dataset from watermarking research to demonstrate the functionality against various watermarked copies and peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics. The PSNR is a measure of how well the watermarked image maintains its original quality, and the NCC reflects how accurately the watermark can be extracted. Our method gives mean PSNR and NCC of 80.50% and 92.51%, respectively.
The traditional hybrid engine calibration method has low efficiency and high cost of manpower and material resources, which can not meet the calibration requirements of complex engine electronic control system. The ca...
详细信息
The traditional hybrid engine calibration method has low efficiency and high cost of manpower and material resources, which can not meet the calibration requirements of complex engine electronic control system. The calibration method based on a mathematical model can greatly reduce the test workload and improve efficiency. Therefore, the black-box model of the engine is constructed by using the results of Spearman correlation analysis, and nine variables are selected as input, at the same time five variables are used as outputs. The improved RSR-BPNNG neural network group method is used to construct the hybrid engine economy and emission model. The model prediction results show that the R2 value of fuel consumption prediction reaches 0.9975, and the R2 value of NOx emission prediction reaches 0.9933, which achieves high precision modeling. On this basis, the performance of the engine under the WHSC cycle is simulated and optimized by the improved adaptive PSO algorithm. The optimization results show that the NOx emission of the engine is reduced by 8.16%, and the fuel consumption is reduced by 4.55%.
In busy offshore waters with high vessel density and intersecting shipping lanes, the risk of collisions and accidents is significantly increased. To address the problem of insufficient feature extraction capability o...
详细信息
In busy offshore waters with high vessel density and intersecting shipping lanes, the risk of collisions and accidents is significantly increased. To address the problem of insufficient feature extraction capability of traditional recurrent neural networks (RNNs) in ship trajectory prediction in busy nearshore areas, this paper proposes a hybrid model based on particleswarmoptimization (PSO), Convolutional Neural Networks (CNN), Residual Networks, Attention Mechanism, and Gated Recurrent Units (GRU), named PSO-CNN-RGRU-Attention, for ship trajectory prediction. This study utilizes real Automatic Identification System (AIS) data and applies the PSO algorithm to optimize the model and determine the optimal parameters, using a sliding window method for input and output prediction. The effectiveness and practicality of the model have been fully verified. Experimental results show that, compared to the PSO-CNN-GRU model, the proposed model improves the longitude by 7.8%, 3.4%, and 1.7% in terms of Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), respectively, and improves the latitude by 48.3%, 62.9%, and 39.2%, respectively. This has significantly contributed to enhancing the safety of ship navigation in the Bohai Strait.
The prediction of remaining useful life (RUL) of lithium-ion batteries is key to the reliability assessment of batteries and affects safe application of batteries. This article introduces a CEEMDAN-RF-MHA-ED-LSTM meth...
详细信息
The prediction of remaining useful life (RUL) of lithium-ion batteries is key to the reliability assessment of batteries and affects safe application of batteries. This article introduces a CEEMDAN-RF-MHA-ED-LSTM method. Using CEEMDAN, the battery capacity data were decomposed to obtain intrinsic mode functions (IMFs), and the weight of each IMF was obtained via the random forest (RF) algorithm. The LSTM neural network was used, the encoder-decoder (ED) structure was introduced, the multi-head attention (MHA) mechanism was used to construct a network model, and the particleswarmoptimization (PSO) algorithm was used to optimize the model parameters. Each IMF was input into the model, and the obtained forecast results were weighted and reconstructed to obtain the final forecast data. This method was validated on the battery dataset released by NASA. Compared with that of the single LSTM model, the mean absolute error of the proposed method decreases by 74%, 62%, 71%, and 55% on the No. 05, 06, 07, and 18th battery datasets, respectively. The root mean square error decreased by 72%, 59%, 70%, and 54%, and the mean absolute percent error decreased by 75%, 65%, 71%, and 58%, respectively. This method can accurately predict battery RUL.
暂无评论