Forecasting Civil Aviation Incident Rate in China Using a Combined Prediction Model

With the rapid development of air transportation, the complexity, importance, and severity of civil aviation safety have gradually become prominent. It is essential to use various data to analyze and predict the level of aviation safety. This paper used a combined prediction model based on Induced Ordered Weighted Averaging (IOWA) operator to forecast the civil aviation incident rate. We compiled and calculated civil aviation incident data and total flight hours from 2008 to 2019 in China and took the civil aviation incident rate (incident numbers per ten thousand flight hours) as the prediction object. First, this paper used the nonlinear regression model, Grey Verhulst model, and Holt-Winters exponential smoothing model to forecast the civil aviation incident rate individually. Then, it used the smallest sum of squared errors as the principle to use a combined prediction model based on the IOWA operator. It can be seen from the experimental results that the prediction accuracy of the combined model is better than single models. Finally, this paper forecasted the civil aviation incident rate in 2020 and 2021. The results showed that the predicted rates are 0.524 and 0.551. Most notably the incident rate will increase significantly compared with 2019.

Forecasting the Number of the Wounded after an Earthquake Disaster Based on the Continuous Interval Grey Discrete Verhulst Model

Earthquake disaster causes serious casualties, so the prediction of casualties is conducive to the reasonable and efficient allocation of emergency relief materials, which plays a significant role in emergency rescue. In this paper, a continuous interval grey discrete Verhulst model based on kernels and measures (CGDVM-KM), different from the previous forecasting methods, can help us to efficiently predict the number of the wounded in a very short time, that is, an “S-shape” curve for the numbers of the sick and wounded. That is, the continuous interval sequence is converted into the kernel and measure sequences with equal information quantity by the interval whitening method, and it is combined with the classical grey discrete Verhulst model, and then the grey discrete Verhulst models of the kernel and measure sequences are presented, respectively. Finally, CGDVM-KM is developed. It can effectively overcome the systematic errors caused by the discrete form equation for parameter estimation and continuous form equation for simulation and prediction in classical grey Verhulst model, so as to improve the prediction accuracy. At the same time, the rationality and validity of the model are verified by examples. A comparison with other forecasting models shows that the model has higher prediction accuracy and better simulation effect in forecasting the wounded in massive earthquake disasters.

Application of GA-BP Neural Network Optimized by Grey Verhulst Model around Settlement Prediction of Foundation Pit

Due to the limitation in the prediction of the foundation pit settlement, this paper proposed a new methodology which takes advantage of the grey Verhulst model and a genetic algorithm. In the previous study, excavation times are often the only factor to predict the settlement, which is mainly because the correspondence between real-time excavation depth and the excavation time is hard to determine. To solve this issue, the supporting times are precisely recorded and the excavation depth rate can be obtained through the excavation time length and excavation depth between two adjacent supports. After the correspondence between real-time excavation depth and the excavation time is obtained, the internal friction angle, cohesion, bulk density, Poisson’s ratio, void ratio, water level changes, permeability coefficient, number of supports, and excavation depth, which can influence the settlement, are taken to be considered in this study. For the application of the methodology, the settlement monitoring point of D4, which is near the bridge pier of the highway, is studied in this paper. The predicted values of the BP neural network, GA-BP neural network, BP neural network optimized by the grey Verhulst model, and GA-BP neural network optimized by the grey Verhulst model are detailed compared with the measured values. And the evaluation indexes of RMSE, MAE, MSE, MAPE, and R 2 are calculated for these models. The results show that the grey Verhulst model can greatly improve the consistency between predicted values and measured values, while the accuracy and resolution is still low. The genetic algorithm (GA) can greatly improve the accuracy of the predicted values, while the GA-BP neural network shows low reflection to the fluctuation of measured values. The GA-BP neural network optimized by the grey Verhulst model, which has taken the advantages of GA and the grey Verhulst model, has extremely high accuracy and well consistency with the measured values.