Research on Thermal Error Modeling of Motorized Spindle Based on BP Neural Network Optimized by Beetle Antennae Search Algorithm

Li, Zhaolong; Zhu, Bo; Dai, Ye; Zhu, Wen-Hong; Wang, Qinghai; Wang, Baodong

doi:10.3390/machines9110286

Cited by 27 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control gas flow rate was kept constant at 3 L/min, the volume of solution in the reactor was 6 L, and the UV light intensity was 40 W. We explored the effect of different initial pH values (3.0, 5.0, 7.0), Fe 2+ concentrations (0, 0.1, 0.3, 0.6 mmol/L), H 2 O 2 concentrations (0, 10, 20, 30 mmol/L) on the degradation of styrene (2000 mg/L) gas [ 18 ]. In order to reduce experimental errors, two sets of parallel trials were performed at the same level for each influence factor.…”

Section: Methodsmentioning

confidence: 99%

“…To realize the optimization effect of BAS on BP, Table 1 lists the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAPE) as evaluation indicators for model prediction [ 18 ], and the results are shown in Table 1 : the BAS-BP decreased by 64.22%, 40.19% and 54.21%, respectively, compared with the BP indicators. The above results indicate that the BP neural network after BAS optimization has a more pronounced improvement in terms of convergence rate or accuracy.…”

Section: Bas-bp Neural Network Modelmentioning

confidence: 99%

See 1 more Smart Citation

Photo-Fenton Degradation Process of Styrene in Nitrogen-Sealed Storage Tank

Zhao

Liu

et al. 2022

Toxics

View full text Add to dashboard Cite

Using styrene as a proxy for VOCs, a new method was developed to remove styrene gas in nitrogen atmospheres. The effect on the styrene removal efficiency was explored by varying parameters within the continuum dynamic experimental setup, such as ferrous ion concentration, hydrogen peroxide concentration, and pH values. The by-products are quantized by a TOC analyzer. The optimal process conditions were hydrogen peroxide at 20 mmol/L, ferrous ions at 0.3 mmol/L and pH 3, resulting in an average styrene removal efficiency of 96.23%. In addition, in this study, we construct a BAS-BP neural network model with experimental data as a sample training set, which boosts the goodness-of-fit of the BP neural network and is able to tentatively predict styrene gas residuals for different front-end conditions.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Bas-bp Neural Network Modelmentioning

confidence: 99%

Photo-Fenton Degradation Process of Styrene in Nitrogen-Sealed Storage Tank

Zhao

Liu

et al. 2022

Toxics

View full text Add to dashboard Cite

show abstract

“…About 90% of the energy of the motorized spindle is converted into heat energy by mechanical energy, so the heat generation of the stator and rotor can be calculated by the energy loss, of which the stator loss accounts for about 50% and the rotor loss accounts for about 25% [22] A02 high-speed motorized spindle rated speed is 9900r/min, rated power is 30kW. Assuming that the motorized spindle is working in the rated state, the heat generated by the stator is 1500W, and the heat generated by the rotor is 750W.…”

Section: Heat Source Calculationmentioning

confidence: 99%

Design and thermal characteristic analysis of electricspindle cooling water jacket

Wang²,

Zhu³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

High-speed motorized spindle is an important component of machine tool, and the influence of heat and deformation generated in the working process on the machining accuracy cannot be ignored. In order to reduce the temperature of the motorized spindle in the machining process, this paper first explore the influence of the flow rate of the motorized spindle cooling water on the cooling water jacket and the overall temperature change. The results indicate that when the flow rate exceeds a certain range, the overall temperature no longer drops, so there is an optimal flow rate in the choice of flow rate. Secondly, to solve the problem of uneven axial temperature distribution of the traditional spiral water jacket, four kinds of cooling water jackets with different structures were proposed. The simulation results show that the difference of temperature distribution inside the serpentine water jacket is small, the overall temperature was reduced by 1.8℃ and the pressure drop was reduced by 62.54kPa. It shows that the serpentine cooling water jacket has better cooling performance and can effectively reduce the thermal deformation of the motorized spindle shafting, so as to achieve the purpose of improving the machining accuracy.

show abstract

“…By updating both the read factor and amplification factor, the convergence effect of the algorithm is improved. In practical application, an error prediction model of machine tool processing accuracy is constructed [6]. In Song et al's study on forest data recognition, the way to improve the accuracy of BP neural network recognition and classification is discussed.…”

Section: Related Workmentioning

confidence: 99%

An Empirical Study on the Training Characteristics of Weekly Load of Calisthenics Teaching and Training Based on Deep Learning Algorithm

Feng

Liu

2022

Scientific Programming

View full text Add to dashboard Cite

Load training is an important part of the daily training of aerobics athletes. Therefore, the research on the characteristics of aerobics movement of athletes in load training has been paid extensive attention by teaching units. Deep learning algorithm in artificial intelligence algorithm is used to study the characteristics of calisthenics teaching and training, which is a beneficial exploration to improve the scientific of calisthenics training programs. The basic principles of the neural network algorithm and implementation process are described. After the basic structure and characteristics of the network are analyzed, a comprehensive solution to optimize and improve the regularized deep belief network algorithm is proposed. The results show that compared with other learning algorithms, the feature classification error rate of the optimized regularized deep belief network algorithm is 6% lower than that of other algorithms. Although the training speed of the model decreases, the convergence period of the deep neural network algorithm can better achieve the extraction accuracy of abstract features of training data when the deep learning period increases. Being less affected by input parameters, the algorithm will have better stability and be more conducive to extracting the features favorable to classification. In the field of deep learning, the advantages of the deep neural networks can effectively classify the training characteristics of aerobics athletes and provide scientific decision-making basis for subsequent teaching and training.

show abstract

Research on Thermal Error Modeling of Motorized Spindle Based on BP Neural Network Optimized by Beetle Antennae Search Algorithm

Cited by 27 publications

References 24 publications

Photo-Fenton Degradation Process of Styrene in Nitrogen-Sealed Storage Tank

Photo-Fenton Degradation Process of Styrene in Nitrogen-Sealed Storage Tank

Design and thermal characteristic analysis of electricspindle cooling water jacket

An Empirical Study on the Training Characteristics of Weekly Load of Calisthenics Teaching and Training Based on Deep Learning Algorithm

Contact Info

Product

Resources

About