Daily and Monthly Suspended Sediment Load Predictions Using Wavelet Based Artificial Intelligence Approaches

In the current study, the efficiency of Wavelet-based Least Square Support Vector Machine （WLSSVM） model was examined for prediction of daily and monthly Suspended Sediment Load （SSL） of the Mississippi River. For this purpose, in the first step, SSL was predicted via ad hoc LSSVM and Artificial Neural Network （ANN） models; then, streamflow and SSL data were decomposed into sub- signals via wavelet, and these decomposed sub-time series were imposed to LSSVM and ANN to simulate discharge-SSL relationship. Finally, the ability of WLSSVM was compared with other models in multi- step-ahead SSL predictions. The results showed that in daily SSL prediction, LSSVM has better outcomes with Determination Coefficient （DC）=o.92 than ad hoc ANN with DC=o.88. However unlike daily SSL, in monthly modeling, ANN has a bit accurate upshot. WLSSVM and wavelet-based ANN （WANN） models showed same consequences in daily and different in monthly SSL predictions, and adding wavelet led to more accuracy of LSSVM and ANN. Furthermore, conjunction of wavelet to LSSVM and ANN evaluated via multi-step-ahead SSL predictions and, e.g., DCLssVM=0.4 was increased to the DCwLsSVM=0.71 in 7- day ahead SSL prediction. In addition, WLSSVM outperformed WANN by increment of time horizon prediction.

Computer Simulation on Metallic Card Clothing Garnett Wire Teeth's Temperature Field & Structure Field in the Process of Quenching Treatment

The quenching process of garnett wire teeth of metallic card clothing heated by flame was researched by use of 3-D finite element method and the equation of boundary condition was established by making use of a model of artificial neural network. The transient temperature field, phase transformation in the heating process, the quenching microstructures and the hardness distribution on quenched garnett wire teeth of metallic card clothing were simulated. The result shows that the maximum error of the hardness between the simulative value and the actual measuring value is 8.0% on only one testing point and errors are all less than 3.0% on other testing points.

Prediction of performance, combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network

This paper explores the use of artificial neural networks （ANN） to predict performance, combustion and emissions of a single cylinder, four stroke stationary, diesel engine operated by thermal cracked cashew nut shell liquid （TC-CNSL） as the biodiesel blended with diesel. The tests were performed at three different injection timings （21°, 23°, 25℃A bTDC） by changing the thickness of the advance shim. The ANN was used to predict eight different engine-output responses, namely brake thermal efficiency （BTE）, brake specific fuel consumption （BSFC）, exhaust gas temperature （EGT）, carbon monoxide （CO）, oxide of nitrogen （NOx）, hydrocarbon （HC）, maximum pressure （Pm~,,） and heat release rate （HRR）. Four pertinent engine operating parameters, i.e., injection timing （IT）, injection pressure （IP）, blend percentage and pecentage load were used as the input parameters for this modeling work. The ANN results show that there is a good correlation between the ANN predicted values and the experimental values for various engine performances, combustion parameters and exhaust emission characteristics. The mean square error value （MSE） is 0.005621 and the regression value ofR2 is 0.99316 for training, 0.98812 for validation, 0.9841 for testing while the overall value is 0.99173. Thus the developed ANN model is fairly powerful for predicting the performance, combustion and exhaust emissions of internal combustion engines.

Fused empirical mode decomposition and wavelets for locating combined damage in a truss-type structure through vibration analysis

Structural health monitoring (SHM) is a relevant topic for civil systems and involves the monitoring, data processing and interpretation to evaluate the condition of a structure, in order to detect damage. In real structures, two or more sites or types of damage can be present at the same time. It has been shown that one kind of damaged condition can interfere with the detection of another kind of damage, leading to an incorrect assessment about the structure condition. Identifying combined damage on structures still represents a challenge for condition monitoring, because the reliable identification of a combined damaged condition is a difficult task. Thus, this work presents a fusion of methodologies, where a single wavelet-packet and the empirical mode decomposition (EMD) method are combined with artificial neural networks (ANNs) for the automated and online identification-location of single or multiple-combined damage in a scaled model of a five-bay truss-type structure. Results showed that the proposed methodology is very efficient and reliable for identifying and locating the three kinds of damage, as well as their combinations. Therefore, this methodology could be applied to detection-location of damage in real truss-type structures, which would help to improve the characteristics and life span of real structures.

Optimal location of interline power flow controller for controlling multi transmission line： A new integrated technique

In this paper, an interline power flow controller （IPFC） is used for controlling multi transmission lines. However, the optimal placement of IPFC in the transmis-sion line is a major problem. Thus, we use a combination of tabu search （TS） algorithm and artificial neural network （ANN） in the proposed method to find out the best placement locations for IPFC in a given multi transmission line system. TS algorithm is an optimization algorithm and we use it in the proposed method to determine the optimum bus combination using line data. Then, using the optimum bus combination, the neural network is trained to find out the best placement locations for IPFC. Finally, IPFC is connected at the best locations indicated by the neural network. Furthermore, using Newton-Raphson load flow algorithm, the transmission line loss of the IPFC connected bus is analyzed. The proposed methodology is implemen- ted in MATLAB working platform and tested on the IEEE-14 bus system. The output is compared with the genetic algorithm （GA） and general load flow analysis. The results are validated with Levenberg-Marquardt back propagation and gradient descent with momentum network training algorithm.