Ming Z.,Wuwei Occupational College
Advanced Materials Research | Year: 2011
Concrete is a mainly and commonly good combined construction material, and is consisted of many well-defined components, so mechanical properties of concrete are very complex. the compressive strength of the concrete is a main criterion in producing concrete, but the test on it is complicated because test components of concrete must be kept in the special condition an tested after 28 days. To simplify the procedures and obtain a reasonable data, the paper presents a method using the system of BP neural network predicting the strength of concrete. the system is trained and tested by using many data of strength of concrete in the past ,the test result shows that the value of the strength of concrete predicted is approximate to the experimental value, and the method presented is very efficient and reasonable in predicting the compressive strength of concrete. © (2011) Trans Tech Publications.
Wang Z.,Key Irrigation Station in Wuwei |
Wang Z.,Chinese Ministry of Water Resources |
Feng H.,Chinese Ministry of Water Resources |
Wen G.,Wuwei Occupational College
Paiguan Jixie Gongcheng Xuebao/Journal of Drainage and Irrigation Machinery Engineering | Year: 2015
In order to achieve efficiently utilize water and fertilizer of seed maize in Shiyanghe basin, field experiments were conducted to study the effect of 4 factors, irrigation quota (A); irrigation frequency (B); topdressing frequency (C); topdressing quota (D), with 3 levels respectively on soil moisture and seed maize yields under ridges and furrows irrigation systems with film mulching. Results showed that irrigation quota had significant effect on the soil moisture of 60-100 cm soil profile in jointing when irrigation quota is more than 400 m3/hm2. In addition, it could significantly extend the vegetative growth cycle of seed maize and improve crop plant height; In comparison with other experimental factors, irrigation quota has the maximum effect, followed by irrigation frequency, topdressing frequency and topdressing quota. The water and nutrient schedule with irrigation quota of 500 m3/hm2 and total irrigation quota of 3 000 m3/hm2 with 6 irrigation frequency (seeding, pre-jointing, later jointing, heading, filling, mature, respectively) and topdressing quota of 200 kg/hm2 in jointing, was effective and optimal in Shiyanghe basin. ©, 2015, Editorial Department of Journal of Drainage and Irrigation Machinery Engineering. All right reserved.
Chen L.-Q.,Changzhou Institute of Technology |
Du L.-L.,Wuwei Occupational College |
Li B.,Changzhou Institute of Technology
Energy Education Science and Technology Part A: Energy Science and Research | Year: 2014
This paper proposed a measuring parameter rebound voltage to realize real-time accurate estimation for state of charge (SOC) of power battery. On the basis of experimental data of SOC, rebound voltage and discharge current, a method which combined the features of grey prediction model and BP neural network prediction model was used to predict the data of SOC. By comparing the prediction data with practical data, the grey neural network method can achieve less error and the prediction accuracy is improved significantly. © Sila Science. All rights reserved.
Chai A.P.,Wuwei Occupational College
Applied Mechanics and Materials | Year: 2013
Time-varying data widely exists anywhere in the objective world, and whose diverse distribution as time is a hybrid stochastic process. Whereas, determining how to achieve knowledge from time-varying database is still an important content of data-mining. In fact, existing techniques of data-mining are difficult to deal with this problem. The paper deeply studies and analyses finite dimension distribution function families of stochastic process and gives out existent theorem of time-varying data classification, proposes a new more effective technique called time-varying datasets classification approach based on slide-window neural networks, and gives out smoothing algorithm and convergent condition with solving this problem as well as simulation examples. The result shows the proposed method is a very effective time-varying data classification method. © (2013) Trans Tech Publications, Switzerland.
Zhao M.,Wuwei Occupational College
2011 International Conference on Electric Information and Control Engineering, ICEICE 2011 - Proceedings | Year: 2011
Recently the earthquake occurs frequently and caused great loss and damage including the slope, the slope stability is very important for the people in the location, its failure will cause a large accident making a numerous loss for the people and society. The paper presents a Neural Network system predicting slope stability and utilizes the characteristics of an artificial intelligence approach and chooses some reasonable case to train and test in the system. As a result, it shows that the Neural Network system presented can be applied in the practical engineer and its accurate can be satisfied for the practical engineer. © 2011 IEEE.