Abstract Engineering ceramics was machining based on grinding technology as major process method assisting with ultrasonic vibration, and the influences of grinding depth and worktable feed rate on the engineering ceramics surface roughness as well as the engineering ceramics topography was also evaluated with the help of surface rough meter and white-light interferometer. The results show that, compared with the engineering ceramics surface grinding... Engineering ceramics was machining based on grinding technology as major process method assisting with ultrasonic vibration, and the influences of grinding depth and worktable feed rate on the engineering ceramics surface roughness as well as the engineering ceramics topography was also evaluated with the help of surface rough meter and white-light interferometer. The results show that, compared with the engineering ceramics surface grinding using conventional process, the surface roughness obviously lowered and the topography improved to some extent when grinding assisting with ultrasonic vibration. Furthermore, the surface conditions was weakened as the grinding depth increases and the worktable feed rate accelerates, which highly reached to 0.332μm and 0.187μm respectively. Read More Read Less

Abstract Landslide dam is formed when a river is blocked by some kind of mass wasting such as the debris and rocks. Landslide dams frequently fail soon and lead to upstream and downstream flooding, which could cause high casualties and economic losses. So it is important to predict landslide dam stability for reasonable subsequent disposal. This study proposes an improved model for landslide dam... Landslide dam is formed when a river is blocked by some kind of mass wasting such as the debris and rocks. Landslide dams frequently fail soon and lead to upstream and downstream flooding, which could cause high casualties and economic losses. So it is important to predict landslide dam stability for reasonable subsequent disposal. This study proposes an improved model for landslide dam disaster events detection based on Support Vector Machine and Ridge Regression. The improved model introduces Support Vector Machine method into traditional Ridge Regression algorithm and get an combinational algorithm, named Combinational Ridge Regression- Support Vector Machine(CRR-SVM) algorithm. This research chooses a record dataset about landslide dam’s variables to test the effectiveness and superiority of the new method; experiment result shows that the boosting approach is more effective than previous methods. Read More Read Less

Abstract It is well known that coalmine gas concentration forecasting is very significant to ensure the safety of mining. Owing to the high-frequency, non-stationary, fluctuations, and chaotic properties of the gas concentration time series, a gas concentration forecasting model utilizing the original raw data often leads to an inability to provide satisfying forecast results. A hybrid forecasting model that integrates wavelet transform and extreme... It is well known that coalmine gas concentration forecasting is very significant to ensure the safety of mining. Owing to the high-frequency, non-stationary, fluctuations, and chaotic properties of the gas concentration time series, a gas concentration forecasting model utilizing the original raw data often leads to an inability to provide satisfying forecast results. A hybrid forecasting model that integrates wavelet transform and extreme learning machine (ELM) termed as WELM (wavelet based ELM) for coalmine gas concentration is proposed. Firstly, the proposed model employ Mallat algorithm to decompose and reconstruct the gas concentration time series to isolate the low-frequency and high-frequency information. Then, ELM model is built for the prediction of each component. At last, these predicted values are superimposed to obtain the predicted values of the original sequence. This method makes an effective separation of the feature information of gas concentration time series and takes full advantage of multi-ELM prediction models with different parameters to achieve divide and rule. Comparative studies with existing prediction models indicate that the proposed model is very promising and can be implemented in a real-time one-step or multi-step ahead prediction. Read More Read Less