scholarly journals Prediction of the Deformation of Aluminum Alloy Drill Pipes in Thermal Assembly Based on a BP Neural Network

2022 ◽  
Vol 12 (2) ◽  
pp. 757
Author(s):  
Xiaofeng Wang ◽  
Baochang Liu ◽  
Jiaqi Yun ◽  
Xueqi Wang ◽  
Haoliang Bai
Keyword(s):  
Neural Network ◽  
Aluminum Alloy ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Thermal Deformation ◽  
Heating Temperature ◽  
Cooling Water ◽  
Interference Fit ◽  
Steel Joint

The connection between the steel joint and aluminum alloy pipe is the weak part of the aluminum alloy drill pipe. Practically, the interference connection between the aluminum alloy rod and the steel joint is usually realized by thermal assembly. In this paper, the relationship between the cooling water flow rate, initial heating temperature and the thermal deformation of the steel joint in interference thermal assembly was studied and predicted. Firstly, the temperature data of each measuring point of the steel joint were obtained by a thermal assembly experiment. Based on the theory of thermoelasticity, the analytical solution of the thermal deformation of the steel joint was studied. The temperature function was fitted by the least square method, and the calculated value of radial thermal deformation of the section was finally obtained. Based on the BP neural network algorithm, the thermal deformation of steel joint section was predicted. Besides, a prediction model was established, which was about the relationship between cooling water flow rate, initial heating temperature and interference. The magnitude of interference fit of steel joint was predicted. The magnitude of the interference fit of the steel joint was predicted. A polynomial model, exponential model and Gaussian model were adopted to predict the sectional deformation so as to compare and analyze the predictive performance of a BP neural network, among which the polynomial model was used to predict the magnitude of the interference fit. Through a comparative analysis of the fitting residual (RE) and sum of squares of the error (SSE), it can be known that a BP neural network has good prediction accuracy. The predicted results showed that the error of the prediction model increases with the increase of the heating temperature in the prediction model of the steel node interference and related factors. When the cooling water velocity hit 0.038 m/s, the prediction accuracy was the highest. The prediction error increases with the increase or decrease of the velocity. Especially when the velocity increases, the trend of error increasing became more obvious. The analysis shows that this method has better prediction accuracy.

scholarly journals Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

2020 ◽  
Vol 10 (8) ◽  
pp. 2926
Author(s):  
Yanzhen Chen ◽  
Yihuai Hu ◽  
Shenglong Zhang ◽  
Xiaojun Mei ◽  
Qingguo Shi
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Prediction Accuracy ◽  
Water Jet ◽  
Erosion Prediction ◽  
Pressure Water ◽  
Erosion Test ◽  
Bp Model

In order to accurately predict the erosion effect of underwater cleaning with an angle nozzle under different working conditions, this paper uses refractory bricks to simulate marine fouling as the erosion target, and studies the optimized erosion prediction model by erosion test based on the submerged low-pressure water jet. The erosion test is conducted by orthogonal experimental design, and experimental data are used for the prediction model. By combining with statistical range and variance analysis methods, the jet pressure, impact time and jet angle are determined as three inputs of the prediction model, and erosion depth is the output index of the prediction model. A virtual data generation method is used to increase the amount of input data for the prediction model. This paper also proposes a Mind-evolved Advanced Genetic Algorithm (MAGA), which has a reliable optimization effect in the verification of four stand test functions. Then, the improved back-propagating (BP) neural network prediction models are established by respectively using Genetic Algorithm (GA) and MAGA optimization algorithms to optimize the initial thresholds and weights of the BP neural network. Compared to the prediction results of the BP and GA-BP models, the R2 of the MAGA-BP model is the highest, reaching 0.9954; the total error is reduced by 47.31% and 35.01%; the root mean square error decreases by 51.05% and 31.80%; and the maximum absolute percentage error decreases by 65.79% and 64.01%, respectively. The average prediction accuracy of the MAGA-BP model is controlled within 3%, which has been significantly improved. The results show that the prediction accuracy of the MAGA-BP prediction model is higher and more reliable, and the MAGA algorithm has a good optimization effect. This optimized erosion prediction method is feasible.

The Research of the Water Quality Prediction Model for the Circulating Cooling Water System

2013 ◽  
Vol 385-386 ◽  
pp. 408-411
Author(s):  
Qiang Gao ◽  
Tian Lu Ma ◽  
Jun Fang Li ◽  
Chen Guang Li
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Water System ◽  
Cooling Water ◽  
Water Quality Prediction ◽  
Network Training ◽  
Prediction Function ◽  
Circulating Cooling Water

Aiming at the common quality faults of scaling and corrosion in circulating cooling water, water quality index were often used to determine the scaling and corrosion of circulating cooling water quality trends. Prediction model of corrosion and scaling rate was built based on BP Neural Network in this paper. The optimal initial individuals were written into the network operating system to optimize the disadvantages of weights and thresholds in BP neural network based on genetic algorithm. The prediction function would output after the network training after comparison of predicted and actual values of the model. The performance of the actual situation was verified to match the model prediction.

Research on Stamping Spring-Back Prediction for Car Body Panel Based on BP Neural Network

2010 ◽  
Vol 97-101 ◽  
pp. 250-254 ◽  
Author(s):  
Xin Jian Zhou
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Front Panel ◽  
Spring Back ◽  
Test Analysis ◽  
Car Body ◽  
Neural Network Prediction ◽  
Mould Design ◽  
Bp Neural Network Model

On the basis of orthogonal test analysis of variance, BP neural network is used to forecast quantitatively the stamping spring-back of front panel of a car body, namely the engine hood, under the conditions of different stamping parameters. Firstly, BP neural network prediction model is established and sample training is done in Matlab. Then, the spring-back prediction using BP neural network and the result of spring-back simulation using Dynaform is compared to verify the precision and stability of the prediction model. Lastly, modification is made to the BP neural network according to practical stamping parameters and an efficient BP neural network model is established. Using this model, stamping spring-back prediction for the front panel of a car body is made. The spring-back prediction could then be used for spring-back compensation in the mould design of the front panel.

Prediction of Sand Thickness Using Seismic Attributes Based on BP-Neural Network

2012 ◽  
Vol 524-527 ◽  
pp. 180-183
Author(s):  
Feng Gao
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Seismic Attributes ◽  
Bp Network ◽  
Sand Body ◽  
Precise Prediction ◽  
Energy Maximum ◽  
Bp Model ◽  
Rms Amplitude

Total energy, maximum peak amplitude and RMS amplitude are sensitive to sand body, and they are non-linear relations with sand thickness. In this study, a three-layer BP neural network is employed to build the prediction model. Nine samples were analyzed by three-layer BP network. The relationships were produced by BP network between sand thickness and the three seismic attributes. The precise prediction results indicate that the three-layer BP network based modeling is a practically very useful tool in prediction sand thickness. The BP model provided better accuracy in prediction than other methods.

scholarly journals Research on GDP Forecast Analysis Combining BP Neural Network and ARIMA Model

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shaobo Lu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Model ◽  
Error Correction ◽  
Relative Error ◽  
Bp Neural Network ◽  
Arima Model ◽  
Forecast Model ◽  
Price Prediction ◽  
The Neural Network

Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model. First, the focus is on the ARMA model in the univariate time series. However, in real life, forecasts are often affected by many factors, so the following introduces the ARIMAX model in the multivariate time series. In the prediction process, the network structure and various parameters of the neural network are not given in a systematic way, so the operation of the neural network is affected by many factors. Each forecasting method has its scope of application and also has its own weaknesses caused by the characteristics of its own model. Secondly, this paper proposes an effective combination method according to the GDP characteristics and builds an improved algorithm BP neural network price prediction model, the research on the combination of GDP prediction model is currently mostly focused on the weighted form, and this article proposes another combination, namely, error correction. According to the price characteristics, we determine the appropriate number of hidden layer nodes and build a BP neural network price prediction model based on the improved algorithm. Validation of examples shows that the error-corrected GDP forecast model is also better than the weighted GDP forecast model, which shows that error correction is also a better combination of forecasting methods. The forecast results of BP neural network have lower errors and monthly prices. The relative error of prediction is about 2.5%. Through comparison with the prediction results of the ARIMA model, in the daily price prediction, the relative error of the BP neural network prediction is 1.5%, which is lower than the relative error of the ARIMA model of 2%.

Sign in / Sign up

Export Citation Format

Share Document