基于高斯混合隐马尔科夫模型与人工神经网络的紧急换道行为预测方法

为了有效降低因驾驶员紧急换道行为而诱发的交通事故，提高道路交通事故链阻断效率，提出一种基于高斯混合隐马尔科夫模型（GMM-HMM）和人工神经网络（ANN）的紧急换道行为预测方法。首先利用GMM-HMM对车辆行驶状态以及驾驶行为连续观察序列进行换道意图辨识，采用ANN预测下一时段的驾驶行为，再预测换道过程中的横向加速度变化率，从而判断紧急换道的危险程度。驾驶员在环仿真实验及实车实验结果表明，该方法预测避险成功率达92.83%，实验避险成功率达90.32%。该方法能有效地对紧急换道行为进行提前警告与干预。     

A new method of predicting the saturation pressure of oil reservoir and its application

Saturation pressure is a vital parameter of oil reservoir which can reflect the oilfield characteristics and determine the oilfield development process, and it is determined by experiments in the laboratory in general. However, there was only one well with saturation pressure test in this target reservoir, and it is necessary to determine whether this parameter is right or not.In this work, we present a new method for quickly determining saturation pressure using machine learning algorithms, including random forest regressor (RF), support vector machine (SVM), decision trees (DT), and artificial neural network (ANN or NN). Using these approaches, saturation pressure was obtained by using the initial solution gas-oil ratio (GOR), temperature, API gravity and other reservoir-fluid data available in the oilfields. Compared with the empirical formula for saturation pressure calculation, the calculated result shows that the accuracy given from machine learning is higher than that from other formulas at home and abroad, and has a good match with the lab test. On the basis of the calculated saturation pressure, it can determine whether the reservoir enters into the stage of dissolved gas drive or not, which also provides the basis for maintaining the reservoir pressure by water injection in advance, rational development decision-making and work over measures.This approach above can provide technical guidance for predicting the saturation pressure in the development of different kinds of reservoirs, including the sandstone reservoirs and carbonate reservoirs.     

Comparison of modeling methods for wind power prediction: a critical study

Prediction of power generation of a wind turbine is crucial, which calls for accurate and reliable models. In this work, six different models have been developed based on wind power equation, concept of power curve, response surface methodology (RSM) and artificial neural network (ANN), and the results have been compared. To develop the models based on the concept of power curve, the manufacturer’s power curve, and to develop RSM as well as ANN models, the data collected from supervisory control and data acquisition (SCADA) of a 1.5 MW turbine have been used. In addition to wind speed, the air density, blade pitch angle, rotor speed and wind direction have been considered as input variables for RSM and ANN models. Proper selection of input variables and capability of ANN to map input-output relationships have resulted in an accurate model for wind power prediction in comparison to other methods.     

Artificial Neural Networks for Prediction of COVID-19 in Saudi Arabia

In this study, we have proposed an artificial neural network (ANN) model to estimate and forecast the number of confirmed and recovered cases of COVID-19 in the upcoming days until September 17, 2020. The proposed model is based on the existing data (training data) published in the Saudi Arabia Coronavirus disease (COVID-19) situation—Demographics. The Prey-Predator algorithm is employed for the training. Multilayer perceptron neural network (MLPNN) is used in this study. To improve the performance of MLPNN, we determined the parameters of MLPNN using the prey-predator algorithm (PPA). The proposed model is called the MLPNN–PPA. The performance of the proposed model has been analyzed by the root mean squared error (RMSE) function, and correlation coefficient (R). Furthermore, we tested the proposed model using other existing data recorded in Saudi Arabia (testing data). It is demonstrated that the MLPNN-PPA model has the highest performance in predicting the number of infected and recovering in Saudi Arabia. The results reveal that the number of infected persons will increase in the coming days and become a minimum of 9789. The number of recoveries will be 2000 to 4000 per day.     

Fluidization using pseudoplastic liquids – Elutriation and ANN modeling

Experimental work on elutriation of irregularly shaped sand particles (0.538–2.03 mm diameter) was carried out in three different Perspex columns (47 mm, 72 mm and 92.3 mm) using different non-Newtonian pseudoplastic liquids (0.4–0.8 kg/m³ SCMC solution). The effects of operating parameters, column diameter, bed weight, particle diameter, particle sphericity, liquid rheological properties on the minimum elutriation velocity were examined. The statistically accepted empirical correlation was developed. ANN model could predict the experimental data of minimum elutriation velocity with a correlation coefficient of 0.9951.     

Prediction of the water content of biodiesel using ANN-MLP: An environmental application

Fuel quality, especially biodiesel, is highly dependent on its water content, and the major sources of water in the fuel relate to the transportation, production, and storage processes. In this present contribution, the multilayer perceptron artificial neural network (MLP-ANN) was applied to predict the water content of biodiesel and diesel blend in terms of temperature and composition. The proposed algorithm was trained and tested by utilizing 400 experimental data points which were extracted from the literature. Based on the results, the MLP-ANN model has great ability to estimate the water content of biodiesel and diesel blend. The R-squared (R²), root mean square error, average absolute relative deviation, and a?bsolute deviation parameters for the total data set are obtained, respectively, as 0.99784, 123919.1172, 3.3632, and 1.17%, which indicate the effective performance suggested by ANN. As the computational study is cheaper and easier than the experimental study, the developed software could be considered as an alternative for laboratory study, and the environmental effect of biodiesel and produced undesired product after biodiesel combustion which is directly related to the water content of biodiesel is estimable with the information released in this study.     

考虑PCA-RBF的变压器标底预测模型研究

针对变压器制造企业投标报价缺乏科学理论指导,准确性低的问题,以准确预估下一批招标的标底价为目标,提出了结合主成分分析(PCA)与人工神经网络(ANN)的变压器标底预测模型-PCA-RBF标底预测模型。模型采用PCA对高维原始变量进行降维处理,提取主成分(PC)作为径向基函数神经网络(RBF)的输入。PCA算法降低了原始变量的维数,去除了各变量间的相关性,在简化ANN结构的同时,提高了预测模型的精度。仿真结果表明,PCA-RBF变压器标底预测模型具有较高的预测精度。     

Simulation based neuro-fuzzy hybrid intelligent PI control approach in four-area load frequency control of interconnected power system

This paper presents a novel control approach of hybrid neuro-fuzzy (HNF) for load frequency control (LFC) of four-area power system. The advantage of this controller is that it can handle the non-linearities, and at the same time it is faster than other existing controllers. The effectiveness of proposed controller in increasing the damping of local and inter area modes of oscillation is demonstrated in four area interconnected power system. Area-1 and area-2 consist of thermal reheat power plant whereas area-3 and area-4 consist of hydro power plant. Performance evaluation is carried out by using fuzzy, ANN, ANFIS and conventional PI and PID control approaches. The performances of the controllers are simulated using MATLAB/Simulink package. The result shows that intelligent HNF controller is having improved dynamic response and at the same time faster than ANN, fuzzy and conventional PI and PID controllers.     

基于BP网络的碳纤维混凝土强度研究

介绍了应用均匀设计理论设计碳纤维混凝土配方的方法,通过所得到的试验数据,运用人工神经网络(ANN)的方法预测碳纤维混凝土抗压强度和劈裂抗拉强度;阐述了采用BP算法建立碳纤维混凝土抗压强度神经网络模型的过程,仿真结果表明,BP网络可成功地建立非线性的强度模型,预测强度可达到较高精度。