Applied Mechanics and Materials Vol. 590

Abstract: The condition of the cutting tool when drilling composite materials is the controlling factor for the surface integrity of hole produced. The high rate of tool wear when drilling composite materials makes finding a way to monitor the condition of the cutting tool without interrupting the drilling process a great necessity. Inspecting the condition of the drill between or during the drilling process is not practical or economical. In an attempt to tackle this problem, a new approach of on-line tool wear monitoring method using an air-coupled audio microphone is proposed. An experimental investigation was conducted on multi-directional carbon fiber reinforced plastic (CFRP) composite material using a high speed steel (HSS) drill. The result shows that, the amplitude of the acoustic signal from the microphone decreases when the amount of flank wear increases and the amplitude of thrust force and torque increases with the increase of the flank wear. This result demonstrates that the proposed approach can be used as an effective and economical tool for on-line monitoring of cutting tool condition.

Abstract: This paper presents a structural design of a methane sensor based on the principle of infrared detection, and designs a program of the experimental calibration. In the conditions of laboratory, different concentrations of methane gas were detected. A concentration inversion formula was proposed by the segmented least-square fitting method. The sensor can measure concentrations of methane in a real-time and accurate way, it contains the functions that digital display and sound and light alarm. The results show that a full-scale concentrations of methane gas can be detected, when the concentration range is in 0-10%, the absolute error is less than 0.09%; when it is more than 10%, the absolute error is less than 0.2%, the response time is less than 15s.

Abstract: In order to identify the content of Ganoderma lucidum powder in Ganoderma lucidum spore powder, diffuse reflectance spectroscopy of samples were collected by the Fourier near-infrared spectrometer. The spectroscopy was pretreated by minimum and maximum normalization and then analyzed with partial least squares (PLS) method. The spectral at 6110 cm^-1 to 4598 cm^-1 was establish PLS model with factors number 10. The result show that the squared correlation coefficient R² between predicted value and true value is 99.99%, and RMSECV is 0.382. In conclusion, Ganoderma lucidum spore powder and Ganoderma lucidum powder can be identified accurately and quickly based on near-infrared spectroscopy and PLS.

Abstract: This paper puts forward the method of acquiring underwater target’s 3D coordinate. It also illustrates the underwater linear structured light measure system. With ICCD technology reducing the influence of underwater laser scattering and Steger algorithm extracting the center of the laser stripe, it presents the method of acquiring underwater target’s 3D coordinate. In the end the method is proved by experiment.

Abstract: Searching for systems with intelligent, flexible, and self-adjusting solutions on imaging, which could provide the contraction of the human operators’ presence, a range of techniques is found. Each one of them can control the process through the assistance of autonomous systems, either software or hardware. Therefore, modeling by traditional computational techniques is quite difficult, considering the complexity and non-linearity of image systems. Compared to traditional models, the approach with Artificial Neural Networks (ANN) behaves well as noise elimination and non-linear data treatment. Consequently, the challenges in the wood industry justify the use of ANN as a tool for process improvement and, therefore, add value to the final product. Additionally, the Artificial Intelligence techniques, such as Neuro-Fuzzy Networks (NFN), have shown efficient, since they combine the ability to learn from examples and to generalize the learned information from the ANNs with the capacity of Fuzzy Logic, in order to transform linguistic variables in rules. Then, ANFIS plays active roles in an effort to reach a specific goal.

Abstract: Based on the weighted inverse topological change method and by introducing a new concept of mass submembers, a dynamical system can be transformed into a static one. Using the properties of the weighted D value, i.e. the weighted D value decreases monotonously with parameter λ increasing; a new method called the weighted D value iteration method is presented for computing the eigenpairs (eigenvalues and eigenvectors). Using this method a series of eigenpairs of a finite element structure can be obtained. It has a merit of simpler algorithm and less computation efforts. Not as the power method, its stability and convergence rate does not depend on the distribution of eigenvalues, and convergent quickly. An example is given to demonstrate the valid of this method.

Abstract: Because of the challenging data association in similar environments, a large number of particles are needed to improve the precision in particle filtering SLAM (simultaneous localization and mapping).An improved particle filter SLAM algorithm based on particle swarm optimization in similar environments is proposed. A multimode proposal distribution is acquired by combining the information of the odometry and the laser scanning. Particles are concentrated to the region of each posterior probability distribution maximum value by PSO. The performance of the conventional particle filter SLAM is improved. The simulation experiment results prove its effectiveness and feasibility.

Abstract: This paper proposes a carbon price forecasting system for the participants to quickly and accurately predict the carbon price. The data including the carbon trading price, oil price, coal price and gas price, are first calculated and the data clusters are embedded in the Excel Database by year and season. The Radial Basis Function Neural Network (RBFNN) is constructed in the searching process. The optimal parameters obtained from the RBFNN enable the learning rate parameters to regulate and improve the predicting errors during the training process, enhancing the accuracy and reliability of predictions. By linking the RBFNN and Excel Database, the training stages of the RBFNN retrieve the input data from the Excel Database so that the efficiency and accuracy of the predicting system can be analyzed. Simulation results in this paper will provide an accurate and real-time method for participants to forecast carbon price and raise the market competition in a carbon trading market.

Abstract: Overlap information usually exits in the high-dimensional data. Misclassified points may be more when affinity propagation clustering is applied to these data. Concerning this problem, a new method combining principal components analysis and affinity propagation clustering is proposed. In this method, dimensionality of the original data is reduced on the premise of reserving most information of the variables. Then, affinity propagation clustering is implemented in the low-dimensional space. Thus, because the redundant information is deleted, the classification is accurate. Experiment is done by using this new method, the results of the experiment explain that this method is effective.

Abstract: In multimodal classification, we look for a set of strategies for mining and exploiting the most informative modalities for a given situation. These strategies are computations performed by the algorithms. In this paper, we propose to consider strategies as advice given to an algorithm by “expert.” There can be several classification strategies. Each strategy makes different assumptions regarding the fidelity of a sensor modality and uses different data to arrive at its estimates. Each strategy may place different trust in a sensor at different times, and each may be better in different situations. In this paper, we introduce a novel algorithm for combining expert strategies to achieve robust classification performance in a multimodal setting. We provide experimental results using real world examples to demonstrate the efficacy of the proposed algorithm.