Kejun Zhu

A hybrid GA-TS algorithm for open vehicle routing optimization of coal mines material

In the open vehicle routing problem (OVRP), the objective is to minimize the number of vehicles and the total distance (or time) traveled. This study primarily focuses on solving an open vehicle routing problem (OVRP) by applying a novel hybrid genetic algorithm and the Tabu search (GA-TS), which combines the GAs parallel computing and global optimization with TSs Tabu search skill and fast local search. Firstly, the proposed algorithm uses natural number coding according to the customer demands and the captivity of the vehicle for globe optimization. Secondly, individuals of population do TS local search with a certain degree of probability, namely, do the local routing optimization of all customer sites belong to one vehicle. The mechanism not only improves the ability of global optimization, but also ensures the speed of operation. The algorithm was used in Zhengzhou Coal Mine and power Supply Co., Ltd.s transport vehicle routing optimization.

Theory and method of genetic-neural optimizing cut-off grade and grade of crude ore

Cut-off grade for ore drawing is a kind of technological method used to control the process of drawing in sublevel caving with no sill pillar. The cut-off grade for ore drawing means the grade of ore in the last time (current time) of ore drawing. Grade of crude ore is the grade of ore entering the milling workshop after ore mixing. Cut-off grade and grade of crude ore are key parameters of production and management in mine system. Genetic algorithm and neural networks nesting method are used in this research to simulate the highly complexity and highly non-linear relationship between variables in mining system, to optimize the cut-off grade and grade of crude ore. The idea is detailed as follows. Cut-off grade and grade of crude ore are joined as chromosome of population for evolution computation; Self-adaptive neural network is used to obtain the local connection between the revenue (fitness function) and chromosome; Genetic algorithm is performed to search the optimal cut-off grade and grade of crude ore globally. The inner layer of nesting is neural networks, which is used to compute loss rate, amount of tailing ore and total cost; the outer layer is evolutionary computation, which is used to get the revenue. The inner layer carries out local approximation, and the outer carries out global search. These two layers carry out the optimization of cut-off grade and grade of crude ore jointly. Take Daye Iron Mine as an example, and the result shows that, the present scheme (cut-off grade is 18%, grade of crude ore is 41-43%) should be improved. During the period of August to November in the year 2007, the optimal cut-off grade is 15.8%, and optimal grade of crude ore is 43.7762-44.1387%, the optimized scheme can improve the present value by 9.01-9.44 million yuan.

A neuro-fuzzy GA-BP method of seismic reservoir fuzzy rules extraction

In this paper, we have prospered a new method to generate fuzzy rules using a genetic algorithm, back propagation, and fuzzy neural networks (FNN) algorithm for seismic reservoir fuzzy rules extraction. This method aims to combine the advantages of fuzzy systems (FS), artificial neural networks (ANN), and GA algorithms and to remedy their drawbacks. The hybrid algorithm can optimize not the number of rules but the membership functions of the antecedent and consequent by adopting multi-encoding of GA. Fuzzy IF/THEN rules were extracted from the optimized FNN.The extracted rules can help to reason the reservoir thickness and decide the optimal drill position in oil field exploration.

An Improved Genetic k-means Algorithm for Optimal Clustering

In the classical k-means algorithm, the value of k must be confirmed in advance. It is difficult to confirm accurately the value of k in reality. This paper proposes an improved genetic k-means algorithm (IGKM) and constructs a fitness function defined as a product of three factors, maximization of which ensures the formation of a small number of compact clusters with large separation between at least two clusters. At last, two artificial and three real-life data sets are considered for experiments that compare IGKM with k-means algorithm, GA-based method and genetic k-means algorithm (GKM) by inter-cluster distance (ITD), inner-cluster distance (IND) and rate of separation exactness. The experiments show that IGKM can automatically reach the optimal value of k with high accuracy

A hybrid intelligent optimization method for multiple metal grades optimization

One of the most important aspects of metal mine design is to determine the optimum cut-off grades and milling grades which relate to the economic efficiency of enterprises and the service life of mines. This paper proposes a hybrid intelligent framework which is based on stochastic simulations and regression, artificial neural network, and genetic algorithms is employed for grade optimization. Firstly, stochastic simulation and regression are used to simulate the uncertainty relations between cut-off grade and the loss rate. Secondly, BP and RBF network are applied to establish two complex relationships from the four variables of cut-off grade, milling grade, geological grade, and recoverable reserves to lost rate and total cost, respectively, in which, BP is used for the one of lost rate, and RBF is for the other. Meanwhile, the real-coding genetic algorithm is performed to search the optimal grades (cut-off grade and milling grade) and the weights of neural networks globally. Finally, the model has been applied to optimize grades of Daye Iron Mine. The results show there are 6. 6978 milling Yuan added compare to unoptimized grades.

Multistage assignment optimization for emergency rescue teams in the disaster chain

Abstract Human resources and potential secondary disasters are often neglected in the existing emergency resource allocation methods. This paper presents a multistage assignment model for rescue teams to dynamically respond to the disaster chain and develops three priority scheduling strategies defined under the burden-benefit accord principle. A designed NSGA-II, C-METRIC and fuzzy logic methods were developed to solve the above multi-objective integer nonlinear programming model. Finally, the experimental scenarios results indicated that the overall performance of the proposed method was satisfactory in comparison with current method regardless of whether the secondary disasters occurred sooner or later. It was demonstrated that the three proposed priority scheduling strategies outperformed the others; however, which of these three priority strategies is most appropriate for a specific disaster situation depends on the maximum rescue time allowed by the disaster.

A better estimate to the contribution rate of education on economic growth in China from 1999 to 2003

The traditional methods of estimating economic contribution rate of education (ECRE) are based on hard computing such as statistical methods, which ignore both the long-term effect of education and the lagged effect of education on economy growth. This paper proposes the fusion method of neural networks, fuzzy systems and genetic algorithms made in the realm of soft computing to estimate the ECRE. Firstly, a target system (a country or a region) is categorized softly according to the level of Science and Technology (ST the second cluster (developing ST the third cluster (underdeveloped S&T) has an ECRE of 1.49% and contains 18 provinces.

Setting up Model of Forecasting Core Reservoir Parameters by Fusion of Soft Computing Methods

The paper utilizes fusion of soft computing methods to distinguish the key attributes of reservoir oil-bearing formation and establishes model with fusion of soft computing methods to forecast these key attributes. The steps as follows: Firstly, use genetic algorithm (GA) and fuzzy c-means nesting algorithm (GA-FCM) to reduce the log attributes of oil-bearing formation and obtain the key attributes that can describe oil-bearing formation of reservoir. Secondly, fuses genetic algorithm and BP neural networks (GA-BP) to construct the fusion model that forecasts the key attributes ,which searches the log attributes and the best number nodes of hidden layer of BP through GA for determining the optimal structure of BP forecasting model. Judge the forecasting model by the error of testing sample. Finally, take oilsk81, oilsk83 and oilsk85 wells of some oil field in China done research and obtain the available results.

China Human Capital Prediction Based on the PCA-BP Artificial Neural Networks

Human capital is one of important factors to decide region economic increasing, which is influenced by various factors. Through Principal Component Analysis we can synthesize numerous indexes, eliminate information overlapping of the sample and reduce the input dimension of BP network. According to the nonlinear feature of human capital system, by using BP network altitudinal nonlinear map, we have efficiently predicted the human capital investment of various regions in China.

The optimal cluster number of FCM in complex economic systems

When modeling the complex economic systems, a target system often need to be categorized into a certain clusters by FCM. The optimal cluster number often is dependent of the selected cluster validity function, but there are so many validity functions proposed, it is difficult to get the optimal cluster number in real target system. A method to get the optimal cluster number of FCM in real systems is proposed: Presets some reasonable cluster numbers, and then chooses a cluster number as the optimal cluster number by some representative validity functions. Testing on the X30 and Bensaid data sets demonstrates the effectiveness and reliability of the proposed method, and finally gives an experiment on Chinapsilas 31 regions according to the level of science and technology (S&T) progress.