Search

Many high and steep slopes are formed in the open pit mining process, whose stability will directly affect the construction and safety. Therefore, it is particularly important to detect and eliminate rough errors of slope monitoring data. This paper proposes an improved two-layer extreme learning machine (TELM) based on particle swarm optimization (PSO) to establish monitoring slope model. In particular, the parameters of the first layer of the whole algorithm are obtained by particle swarm optimization algorithm, and the parameters of the second layer are calculated through a new solution method. First, some basic principles and concepts of extreme learning machine are introduced, and the algorithm thought, basic principles and related derivation of the improved two-layer extreme learning machine in this paper are emphatically discussed. A better mapping relationship between the input space and the output space is found through the parameter solution method, which improves the precision of the algorithm. Then, the data collection and traditional gross error elimination methods are studied. Finally, in order to test the ability of the two hidden layer extreme learning machine to solve the slope monitoring problem, the algorithm is applied to the gross error elimination of the slope data. The experimental results show that compared with the traditional gross error elimination method and ELM algorithm, the proposed method has higher precision, stronger robustness, and more practicability.

Precision manufacturing engineering requires not only excellent materials but also precise machining methods. The point contact cutting is widely applied to precision turning, milling, grinding, and so on. However, the machining principle and the surface topography formation process of the point contact cutting are not well described mathematically. To solve the problem, we proposed a new surface topography analysis method considering vibration in this paper. First, based on the geometry topology theory, we reduced the dimension of the point contact cutting process. Moreover, the surface topography displacement formula was derived. Finally, the relationships between the influence factors (the shape of the cutting tools, the cutting parameters, and vibration) and the surface topography displacement were analyzed and explored. The surface topography analysis method proposed in this paper provides the theoretical foundation for designing, controlling, and optimizing the point contact cutting process.

Reliability of the CNC machine tool (abbreviated as machine tool) relates to the product's reliability and has great influence on the manufacturing process. The traditional reliability statistical evaluation method of the machine tool neglects the influence of the mission profile and load profile (M&L), it causes that the evaluation result is not accurate enough to provide accurate references for the reliability-related works under specific M&Ls such as the preventive maintenance, product improvement, etc. To address these defects, this paper proposes an improved reliability statistical evaluation method considering the M&L. Firstly, the machine tool is decomposed by the meta-action decomposition method, and the mission profile of the machine tool is represented by the meta-action chain (MC). Secondly, load profile representation indicators of the machine tool are extracted based on the load composition and cutting force calculation. Then, the mapping model between the M&L and the machine tool's reliability is established using the radial basis function (RBF) neural network. Finally, the improved reliability statistical evaluation method is illustrated and validated by the engineering practical application. Comparing the evaluation results of the two statistical evaluation methods, it shows that the improved reliability statistical evaluation method is more accurate than the traditional reliability statistical evaluation method, under specific M&Ls, so that it can provide more accurate references for the reliability-related works.

The seamless tube, being widely used in the automobile, aviation, petroleum, chemical, building, boiler, and military industries, is called the “blood vessel of industry.”The demands for high quality seamless tubes are increasing continuously. Piercing is the first deformation process in seamless tube production and has great influence on the quality of the product. This paper takes the Diescher piercer as the object of study and builds the DEFORM finite-element model of piercing process. The DEFORM model of piercing process can substitute for practical production and serve as a simulation platform of the production process. The DEFORM model can be used for the optimization of the process parameters and the prediction of quality, and it also greatly reduces the debugging time and the production cost. Therefore, the model has great theoretical significance and is of great value in practical use. Finally, by combining the DEFORM finite-element model with the ensemble OSC-PLS-ELM mathematical model, we build the hybrid model, which further increases the precision of the quality forecast. The ensemble OSC-PLS-ELM method has the advantages of both the PLS and ELM, i.e., the characteristics of robustness and feature extraction of the PLS method and the quick nonlinear processing capability of ELM.

The demand for coal has been on the rise in modern society. With the number of opencast coal mines decreasing, it has become increasingly difficult to find coal. Low efficiencies and high casualty rates have always been problems in the process of coal exploration due to complicated geological structures in coal mining areas. Therefore, we propose a new exploration technology for coal that uses satellite images to explore and monitor opencast coal mining areas. First, we collected bituminous coal and lignite from the Shenhua opencast coal mine in China in addition to non-coal objects, including sandstones, soils, shales, marls, vegetation, coal gangues, water, and buildings. Second, we measured the spectral data of these objects through a spectrometer. Third, we proposed a multilayer extreme learning machine algorithm and constructed a coal classification model based on that algorithm and the spectral data. The model can assist in the classification of bituminous coal, lignite, and non-coal objects. Fourth, we collected Landsat 8 satellite images for the coal mining areas. We divided the image of the coal mine using the constructed model and correctly described the distributions of bituminous coal and lignite. Compared with the traditional coal exploration method, our method manifested an unparalleled advantage and application value in terms of its economy, speed, and accuracy.