Multidimensional research on agrometeorological disasters based on grey BP neural network

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Bingjun Li ◽  
Shuhua Zhang
Keyword(s):  
Neural Network ◽  
Natural Disaster ◽  
Bp Neural Network ◽  
Henan Province ◽  
Assessment System ◽  
Systematic Analysis ◽  
Content Type ◽  
Analysis And Evaluation ◽  
Grain Crops ◽  
Disaster Vulnerability

PurposeThe purpose of this study to provide a reference basis for effectively managing the risk of agrometeorological disasters in Henan Province, speeding up the establishment of a scientific and reasonable system of agrometeorological disasters prevention and reduction and guaranteeing grain security.Design/methodology/approachFirstly, according to the statistical data of areas covered by natural disaster, areas affected by natural disaster, sown area of grain crops and output of grain crops from 1979 to 2018 in Henan Province, China. We have constructed an agrometeorological disaster risk assessment system for Henan province, China, which is composed of indicators such as rate covered by natural disaster, rate affected by natural disaster, disaster coefficient of variation and disaster vulnerability. The variation characteristics of agrometeorological disasters in Henan Province and their effects on agricultural production are analyzed. Secondly, the grey relational analysis method is used to analyze the relation degree between the main agrometeorological disaster factors and the output of grain crops of Henan Province. Based on the grey BP neural network, the rate covered by various natural disaster and the rate affected by various natural disaster are simulated and predicted.FindingsThe results show that: (1) the freeze injury in the study period has a greater contingency, the intensity of the disaster is also greater, followed by floods. Droughts, windstorm and hail are Henan Province normal disasters. (2) According to the degree of disaster vulnerability, the ability to resist agricultural disasters in Henan Province is weak. (3) During the study period, drought and flood are the key agrometeorological disasters affecting the grain output of Henan Province, China.Practical implicationsThe systematic analysis and evaluation of agrometeorological disasters are conducive to the sustainable development of agriculture, and at the same time, it can provide appropriate and effective measures for the assessment and reduction of economic losses and risks.Originality/valueBy calculating and analyzing the rate covered by natural disaster, the rate affected by natural disaster, disaster coefficient of variation and disaster vulnerability of crops in Henan Province of China and using grey BP neural network simulation projections for the rate covered by various natural disaster and the rate affected by various natural disaster, the risk assessment system of agrometeorological disasters in Henan is constructed, which provides a scientific basis for systematic analysis and evaluation of agrometeorological disasters.

Prediction and analysis of compressive strength of recycled aggregate thermal insulation concrete based on GA-BP optimization network

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jinsong Tu ◽  
Yuanzhen Liu ◽  
Ming Zhou ◽  
Ruixia Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Compressive Strength ◽  
Thermal Insulation ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Training Sample ◽  
Recycled Aggregate ◽  
Generalization Performance ◽  
Content Type

Purpose This paper aims to predict the 28-day compressive strength of recycled thermal insulation concrete more accurately. Design/methodology/approach The initial weights and thresholds of BP neural network are improved by genetic algorithm on MATLAB 2014 a platform. Findings Genetic algorithm–back propagation (GA-BP) neural network is more stable. The generalization performance of the complex is better. Originality/value The GA-BP neural network based on the training sample data can better realize the strength prediction of recycled aggregate thermal insulation concrete and reduce the complex orthogonal experimental process. GA-BP neural network is more stable. The generalization performance of the complex is better.

Paste-filling weighing control system optimization based on neural network

2017 ◽  
Vol 14 (2) ◽  
pp. 155-158 ◽  
Author(s):  
Guimei Wang ◽  
Yong Shuo Zhang ◽  
Lijie Yang ◽  
Shuai Zhang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Coal Mine ◽  
Bp Neural Network ◽  
Back Propagation ◽  
System Optimization ◽  
Filling Material ◽  
Content Type ◽  
Control Precision ◽  
Filling System

Purpose This paper aims to optimize the weighing control system and compensate weighing error for weighing control system of coal mine paste-filling weighing control system. Design/methodology/approach The process of the paste-filling weighing control system is analyzed and the mathematical model of the paste-filling material weight is established. Then, the back-propagation (BP) neural network is used to optimize the control system and compensate the weighing error. Findings Without the BP neural network, the weighing error of the paste-filling control system is more than 3 per cent, whereas after optimization with the BP neural network, the weighing error is less than 1 per cent. With the simulation results, it is seen that the weighing error of the paste-filling control system decreases and the accuracy of the weighing control system improves and optimizes. Originality/value The method can be further used to improve the control precision of the coal mine paste-filling system.

Prediction of viscosity of ternary tin-based lead-free solder melt using BP neural network

2020 ◽  
Vol 32 (3) ◽  
pp. 173-180
Author(s):  
Min Wu ◽  
Bailin Lv
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Lead Free ◽  
Lead Free Solder ◽  
Content Type ◽  
Free Solder ◽  
Bp Neural Network Model ◽  
Lead Free Solders

Purpose Viscosity is an important basic physical property of liquid solders. However, because of the very complex nonlinear relationship between the viscosity of the liquid ternary Sn-based lead-free solder and its determinants, a theoretical model for the viscosity of the liquid Sn-based solder alloy has not been proposed. This paper aims to address the viscosity issues that must be considered when developing new lead-free solders. Design/methodology/approach A BP neural network model was established to predict the viscosity of the liquid alloy and the predicted values were compared with the corresponding experimental data in the literature data. At the same time, the BP neural network model is compared with the existing theoretical model. In addition, a mathematical model for estimating the melt viscosity of ternary tin-based lead-free solders was constructed using a polynomial fitting method. Findings A reasonable BP neural network model was established to predict the melt viscosity of ternary tin-based lead-free solders. The viscosity prediction of the BP neural network agrees well with the experimental results. Compared to the Seetharaman and the Moelwyn–Hughes models, the BP neural network model can predict the viscosity of liquid alloys without the need to calculate the relevant thermodynamic parameters. In addition, a simple equation for estimating the melt viscosity of a ternary tin-based lead-free solder has been proposed. Originality/value The study identified nine factors that affect the melt viscosity of ternary tin-based lead-free solders and used these factors as input parameters for BP neural network models. The BP neural network model is more convenient because it does not require the calculation of relevant thermodynamic parameters. In addition, a mathematical model for estimating the viscosity of a ternary Sn-based lead-free solder alloy has been proposed. The overall research shows that the BP neural network model can be well applied to the theoretical study of the viscosity of liquid solder alloys. Using a constructed BP neural network to predict the viscosity of a lead-free solder melt helps to study the liquid physical properties of lead-free solders that are widely used in electronic information.

Research on configuration design and operation effect evaluation for ultra high voltage (UHV) vertical insulator cleaning robot

2019 ◽  
Vol 47 (1) ◽  
pp. 90-101 ◽  
Author(s):  
Yu Yan ◽  
Wei Jiang ◽  
An Zhang ◽  
Qiao Min Li ◽  
Hong Jun Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Motion Planning ◽  
High Voltage ◽  
Bp Neural Network ◽  
Evaluation Method ◽  
Effect Evaluation ◽  
Content Type ◽  
Network Training ◽  
Cleaning Robot ◽  
Physical Prototype

Purpose This study aims to the three major problems of low cleaning efficiency, high labor intensity and difficult to evaluate the cleaning effect for manual insulators cleaning in ultra high voltage (UHV) converter station, the purpose of this paper is to propose a basic configuration of UHV vertical insulator cleaning robot with multi-freedom-degree mechanical arm system on mobile airborne platform and its innovation cleaning operation motion planning. Design/methodology/approach The main factors affecting the insulators cleaning effect in the operation process have been analyzed. Because of the complex coupling relationship between the influencing factors and the insulators cleaning effect, it is difficult to establish its analytical mathematical model. Combining the non-linear mapping and approximation characteristics of back propagation (BP) neural network, the insulator cleaning effect evaluation can be abstracted as a non-linear approximation process from actual cleaning effect to ideal cleaning effect. An evaluation method of robot insulator cleaning effect based on BP neural network has been proposed. Findings Through the BP neural network training, the robot cleaning control parameters can be obtained and used in the robot online operation control, so that the better cleaning effect can be also obtained. Finally, a physical prototype of UHV vertical insulator cleaning robot has been developed, and the effectiveness and engineering practicability of the proposed robot configuration, cleaning effect evaluation method are all verified by simulation experiments and field operation experiments. At the same time, this method has the remarkable characteristics of sound versatility, strong adaptability, easy expansion and popularization. Originality/value An UHV vertical insulator cleaning robot operation system platform with multi-arm system on airborne platform has been proposed. Through the coordinated movement of the manipulator each joint, the manipulator can be positioned to the insulator strings, and the insulator can be cleaned by two pairs high-pressure nozzles located at the double manipulator. The influence factors of robot insulator cleaning effect have been analyzed. The BP neural network model of insulator cleaning effect evaluation has been established. The evaluation method of robot insulator cleaning effect based on BP neural network has also been proposed, and the corresponding evaluation result can be obtained through the network training. Through the system integration design, the robot physical prototype has been developed. For the evaluation of other operation effects of power system, the validity and engineering practicability of the robot mechanism, motion planning and the method for evaluating the effect of robot insulator cleaning have been verified by simulation and field operation experiments.

Research on the influence of background light on the accuracy of a three-dimensional coordinate measurement system based on dual-PSD

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xiaohong Lu ◽  
Yu Zhou ◽  
Jinhui Qiao ◽  
Yihan Luan ◽  
Yongquan Wang
Keyword(s):  
Neural Network ◽  
Measurement System ◽  
Bp Neural Network ◽  
Measurement Accuracy ◽  
Three Dimensional ◽  
Electrical Method ◽  
Content Type ◽  
Coordinate Measurement ◽  
Background Light ◽  
Three Dimensional Coordinate

Purpose The purpose of this paper is to analyze the measurement error of a three-dimensional coordinate measurement system based on dual-position-sensitive detector (PSD) under different background light. Design/methodology/approach The mind evolutionary algorithm (MEA)-back propagation (BP) neural network is used to predict the three-dimensional coordinates of the points, and the influence of the background light on the measurement accuracy of the three-dimensional coordinates based on PSD is obtained. Findings The influence of the background light on the measurement accuracy of the system is quantitatively calculated. The background light has a significant influence on the prediction accuracy of the three-dimensional coordinate measurement system. The optical method, electrical method and photoelectric compensation method are proposed to improve the measurement accuracy. Originality/value BP neural network based on MEA is applied to the coordinate prediction of the three-dimensional coordinate measurement system based on dual-PSD, and the influence of background light on the measurement accuracy is quantitatively analyzed.

Predicting delays in prefabricated projects: SD-BP neural network to define effects of risk disruption

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ying Zhao ◽  
Wei Chen ◽  
Mehrdad Arashpour ◽  
Zhuzhang Yang ◽  
Chengxin Shao ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Input Parameter ◽  
Model System ◽  
Extreme Condition ◽  
Content Type ◽  
Schedule Delay ◽  
Wide Range ◽  
Delay Prediction

PurposePrefabricated construction is often hindered by scheduling delays. This paper aims to propose a schedule delay prediction model system, which can provide the key information for controlling the delay effects of risk-related factors on scheduling in prefabricated construction.Design/methodology/approachThis paper combines SD (System Dynamics) and BP (Back Propagation) neural network to predict risk related delays. The SD-based prediction model focuses on dynamically presenting the interrelated impacts of risk events and activities along with workflow. While BP neural network model is proposed to evaluate the delay effect for a single risk event disrupting a single job, which is the necessary input parameter of SD-based model.FindingsThe established model system is validated through a structural test, an extreme condition test, a sensitivity test, and an error test, and shows an excellent performance on aspect of reliability and accuracy. Furthermore, 5 scenarios of case application during 3 different projects located in separate cities prove the prediction model system can be applied in a wide range.Originality/valueThis paper contributes to academic research on combination of SD and BP neural network at the operational level prediction, and a practical prediction tool supporting managers to take decision-making in a timely manner against delays.

Estimation of construction project building cost by back-propagation neural network

2019 ◽  
Vol 18 (3) ◽  
pp. 601-609
Author(s):  
Qinghua Jiang
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Bp Neural Network ◽  
Cost Estimation ◽  
Back Propagation ◽  
Estimation Accuracy ◽  
Average Error ◽  
Estimation Model ◽  
Content Type ◽  
Building Cost

Purpose Building cost is an important part of construction projects, and its correct estimation has important guiding significance for the follow-up decision-making of construction units. Design/methodology/approach This study focused on the application of back-propagation (BP) neural network in the estimation of building cost. First, the influencing factors of building cost were analyzed. Six factors were selected as input of the estimation model. Then, a BP neural network estimation model was established and trained by ten samples. Findings According to the experimental results, it was found that the estimation model converged at about 85 times; compared with radial basis function (RBF), the estimation accuracy of the model was higher, and the average error was 5.54 per cent, showing a good reliability in cost estimation. Originality/value The results of this study provide a reliable basis for investment decision-making in the construction industry and also contribute to the further application of BP neural network in cost estimation.

Prediction on Number of Agricultural Pumps in Henan Province of China Based on BP Neural Network

2012 ◽  
Vol 155-156 ◽  
pp. 1170-1174
Author(s):  
Jian Wei Li ◽  
Xiu Shan Wang ◽  
Yu Gui Tang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Statistical Data ◽  
Henan Province ◽  
Future Market ◽  
Market Conditions ◽  
Absolute Value ◽  
The Neural Network ◽  
Relative Errors

To understanding future market conditions of agricultural pumps in Henan province, need to predict numbers of agricultural pumps at each year-end. Expatiated the principle of prediction based on BP neural network, and constructed the model of prediction. The BP neural network was trained with normalized statistical data of agricultural pumps in Henan province from 1990 to 2010, and gained parameters of the neural network. Test shows the model has high predictive precision. The average absolute value of predicted relative errors is 1.333%. Numbers of agricultural pumps at each year-end in Henan province of China from 2011 to 2015 were predicted, and the trend was also presented.

Sign in / Sign up

Export Citation Format

Share Document