Changjun Zhu

ANN based on PSO for surface water quality evaluation model and its application

In view of the deficiency of the traditional methods, according to the analysis of surface water in Suzhou city, a BP neural network model is proposed to evaluate water quality. Firstly The present situation and changing trends of surface water are analyzed. The structure of BP model is described and the choice of hidden layer is also optimized. Finally, the proposed model was applied to evaluate the surface water quality in Suzhou city. BP neural network is trained using PSO. The evaluation result was compared with that of the BP neural network method without training by PSO and the reported results. It indicated that the performance of proposed neural network model is practically feasible in tha application of water quality assessment and its operation is simple.

Application of Grey Relation Analysis in Evaluation of Water Quality

In view of the deficiency of classic method evaluating water quality. A grey relational analysis model is proposed to evaluate water quality in river. The principle of grey relational analysis and its process are introduced. Suzhou river was selected and assessed by using this method. And it was found that, compared with the fuzzy complex judgment method, the result was remarkably different. The possible reason for this was given. Additionally, this paper proposes preventive measures against river contamination, which could provide a basis for marine environment protection.

Fuzzy Neural Network Model and Its Application in Water Quality Evaluation

In view of the defect of traditional water quality evaluation model, based on fuzzy neural network theory, a new model of fuzzy neural network (FNN) comprehensive evaluation is developed to evaluate surface water quality in Suzhou. Fuzzy neural network is a new type neural network consisting Radical Basis network and compete neural network, which is simple in structure, easy for training and wide used. FNN model is applied to evaluate water quality at representative sections in Suzhou surface area from the year 1999-2002. The results indicate that FNN model is suitable for water quality evaluation. By analysis, it is important to pay attention to bring into effective measures for pollution control.

Management Decision System of Regional Water Resources

In order to manage the water resources well, regional water resources management decision system, based upon surface water, groundwater and atmosphere water information data base and focused on numerical simulation models, is set up by use of numerical model and computer technique, according to idea of decision-making variable deduction. It can afford a series of dynamic and scientific decision for the reasonable development of regional water resources in Handan area.

Applied research on the hydraulic engineering management system based on C/S

This paper describes an application system process that is developed by combining the Delphi language with software engineering theory knowledge. It elaborates the whole process of designing in detail in the process of developing system, gives the chart of system function and partial source code, states the steps of system tests together with check and accept at last. The system is belongs to hydraulic engineering Management System, which adapts to client/server database mode, it is linked by BDE and SQL Server. Its main function is gaining a clear condition of the using of human resources real-time and dynamically, to overall financial planning and know the project progress. Not only does it achieves the equitable distribution of authority of a user, the dynamic allocation of human resource, the input of employee man-hour information, query, statistics, the distribution of company or department projects, but also it inputs the data statistics in man-hour information to excel texts, and it can link to printers or other hardwares. One of the sites in company can get the precise data information through the link to a master server.

RBF neural network model and its application in the prediction of output in oilfield

In view of difficulty to predict the output in oilfield which affected by multi-variables, RBF neural network model is set up to predict the output in oilfield because the classic statistics method and static model can not meet the demand of precision to the nonlinear and uncertain system. Effective depth, permeability, porosity and water content are as the input of neural network and oilfield output as the output of the neural network. The results show that this prediction approach is very effective and has higher accuracy. The results show that the model can forecast the oilfield output with accuracy comparable to other classic method. So the RBF neural network is an effective method to predict the oilfield output with high accuracy. The application of this approach can supply reliable data for the development of oilfield and decrease the risks for the exploitation.

Design and implementation of electronic commerce website

This paper elaborates the structure of electronic commerce; it designs the function module and database of electronic, as well as the electronic commerce website of FEIYA science and technology book store gets a further development. Its main technology is developing the database application based on website. It adopts the C++ builder of Borland Company, while the method of website development — ISAPI is used frequently. We simulate books trade which is popular at present on network, membership registration, query online together with shopping online and so on functions can be realized.

Prediction of Groundwater Quality Using Combined Grey Neural Network Model

In view of the defect that the grey method can only predict the tendency approximately and artificial neural network can not predict the future tendency really, a new combined grey neural network model was proposed. This paper mainly analyses the groundwater quality and establishes their mathematical model based on the groundwater monitoring data of one area by combined grey neural network method. It predicts various tendency of groundwater quality in this area in the future. Case study indicates that precision of the model is rather high and its popularization significance is better than the other models, and has some practical value when being used in the prediction of groundwater quality analysis.

Simulation of River Water Quality Using Grey Numerical Model

With the development of social and economic, the pollution in river is worse. It is very important to study river pollution. In view of the uncertainty of river water pollution, Velocity and dispersion coefficient and attenuation in river are considered as uncertainty parameters and expressed as grey parameters. One dimensional gray numerical water quality model is developed according to gray theory. The model has an especial structure and the gray numerical arithmetic solving this kind model is given and compared with the classic arithmetic. The simulation results are an grey scope not an exact value. The result shows that the algorithm is feasible and reliable to simulate water quality

Determination of Trace Chromium in the Fu-Yang River by CAS and CTMAB Spectrophotometry

Because of the toxicity property of chromium in the water, it is important for the water environment to monitor the trace chromium with a kind of simple and sensitive method. Spectrophotometry of CAS and CTMAB is adopted to determine chromium in the Fu-yang river. The results indicates that the detected limit of this method is 0.0005 ug/mL, the mark-on recovery ranged from 87.7% to 97.0% and relative standard deviation is 5.0%. In addition, several problems needing attention about experiment process are posed in this paper.