Applied Mechanics and Materials Vol. 598

Abstract: To get better solution by improving the mutation strategy of Differential Evolution algorithm, a fractal mutation strategy is introduced. The fractal mutation factor of the proposed Fractal Mutation factor Differential Evolution (FMDE) algorithm is simulated by fractal Brownian motion with a different Hurst index. The new algorithm is test on 25 benchmark functions presented at 2005 IEEE Congress on Evolutionary Computation (CEC2005). The optimization results of at least 10 benchmark functions are significantly better than the results obtained by JADE and CoDE, and most of the rest of the test results are approximate. This shows that FMDE can significantly improve the accuracy and adaptability to solve optimization problems.

Abstract: This article explored the design and implementation problems of Sustainability Assessment Data Warehouse for Shanghai Airport. According to the characteristics of Shanghai airport, the airport data collection platform layer and six theme databases were designed in this paper. This paper also designed the operator assessment models and the user evaluation models, which strong guaranteed and supported the validity of the evaluation of sustainable development at the airport.

Abstract: A classification processing method of cotton foreign fibers was proposed based on probability statistics and BP neural network. Due to the origin was wide, the type was complex and the characteristic of cotton foreign fibers was different, it was difficult to build a model on classification and identification of cotton foreign fibers in the detection process of cotton spinning enterprises. This method could solve this question elegantly. Firstly, obtained the sample data by extracting the mean value of R, G, B in the fiber image and built a model about BP neural network. Then, classified 2-types cotton foreign fibers by calculating absolute value and variance of the feature vector based on probability statistics. Finally, processed the extraction features according to the different types image. The cross-validation experiment, the results show that the method combining the probability statistics and BP neural network can classify the cotton foreign fibers efficiently, and the effect is better when the types of cotton foreign fibers corresponding to the different features extraction methods The cross validation experiment, results showed that the combination can effectively identify the classification of foreign fibers and BP network based on probability and statistics, and different types of contton foreign fiber used different feature extraction methods, the effect is remarkable.

Abstract: In this paper, a method is proposed using the motion vector in Gabor space to recognize smoke region. Smoke orbit is described as up-forward and has some similar sharp in feature space. The propose method is assessed by calculating 45,90,135 degree upward vectors , and determined the possibility of smoke region. Different images were tested using smoke video scenes, and it meets the desired expectation. The next step will be in-depth study represents a high-dimensional space .

Abstract: In order to make the GPS monitoring data of coal mine subsidence useful and effective in engineering practice, this paper tries to analyze the exceptional handling processing model of the GPS monitoring data of coal mine subsidence under the guidance of the principle of support vector machine (SVM) regression, its calculating method and the application of regression program produced by MATLAB. By comparing the result of the exceptional handling processing model established on practical measured data with the one of the polynomial function fitting, this thesis proves that the application of vector regression algorithm in studies on the exceptional handling processing model of the GPS monitoring data is highly effective.

Abstract: In order to control an unmanned helicopter accurately and reliably, it is necessary to have a precise mathematical model of its dynamics. This paper presents a new timedomain identification method and process for full state space model of small-scale unmanned helicopters. The identification method is called ISAcwPEM (Improved Simulated Annealing combined with Prediction Error Method), which is not sensitive to initial point selection and doesn’t require frequency-sweeping inputs. Firstly, the primary parameters to be identified are selected by model sensitivity analysis. After that, the improved simulated annealing algorithm runs in a distributed computing platform to figure out a 13-order state space model of the SJTU T-REX700E small-scale unmanned helicopter (consisting of a cruise modal and a hover modal). Then the iterative Prediction Error Method (PEM) is used to optimize the model. In addition, the time-delay term and the trim term are estimated and added to the model. Finally, the effectiveness of the identification method is well validated by real outdoor flight experimental results.

Abstract: A new type of fuzzy inference systems (FIS) is presenting. It is based on Takagi-Sugeno fuzzy inference system. New FIS has been called the enhanced fuzzy regression (EFR). In opposition to the Takagi-Sugeno, new type of FIS has fuzzy coefficients in right parts of the fuzzy rules. Fuzzy approximation theorem has been proved for the EFR. We have suggested learning procedure for EFR inference system.

Abstract: While the development of automobile has provided convenience to people's daily life and economic activities, vehicle exhaust has also brought serious environmental pollution. The harmful gas produced by cars contains hydrocarbons and hydronitrogens. Among them, acetylene gas which belongs to atmospheric trace gases, cannot be affected by environmental factors. With the theory of tunable diode laser absorption spectroscopy (TDLAS) technique, wavelength modulation and harmonic detecting technique, this system uses the intelligent data acquisition and processing system based on MSP430 to detect acetylene gas in real-time and display the vehicle exhaust. The system has a good stability, high measuring accuracy and long service life. It is cheap and easy to maintain. It realized low power design.

Abstract: As one of the efficient means of data acquisition, remote sensing data play an important role in many areas of life through the development of technology and the improvement of spatial resolution. In this paper, the application of remote sensing data on dynamic monitoring of coastline in the Yellow River Delta was analyzed. The results indicate that the using of remote sensing data was more scientific and efficient than the traditional methods, and the analysis results can provide a theoretical basis for the ecological protection in the Yellow River Delta.

Abstract: This article states the error factors in parts of data acquisition and data processing of reverse engineering, and gives optimization suggestions in practical applications. It provides a more practical method for manufacturing products closer to the samples.