Matrix Search Algorithm Research Articles

Fault diagnosis method of bearing utilizing GLCM and MBASA-based KELM

In this study, fault diagnosis method of bearing utilizing gray level co-occurrence matrix (GLCM) and multi-beetles antennae search algorithm (MBASA)-based kernel extreme learning machine (KELM) is presented. In the proposed method, feature extraction of time–frequency image based on GLCM is proposed to extract the features of the bearing vibration signal, and multi-beetles antennae search algorithm-based KELM (MBASA-KELM) is presented to recognize the states of bearing. KELM employs the kernel-based framework, which has better generalization than traditional extreme learning machine, and it is necessary to look for an excellent optimization algorithm to select appropriate regularization parameter and kernel parameter of the KELM model because these parameters of the KELM model can affect its performance. As traditional beetle antennae search algorithm only employs one beetle, which is difficult to find the optimal parameters when the ranges of the parameters to be optimized are wide, multi-beetles antennae search algorithm (MBASA) employing multi-beetles is presented to select the regularization parameter and kernel parameter of KELM. The experimental results demonstrate that MBASA-KELM has stronger fault diagnosis ability for bearing than LSSVM, and KNN.

The equilibrium and form-finding of general tensegrity systems with rigid bodies

We develop a general approach to study the equilibrium and form-finding of any general tensegrity systems with rigid bodies. The equilibrium equations are derived in an explicit form in terms of a nodal coordinate and orientation parameter as the minimal coordinate. The nodal vector consists of nodes (either free or pinned) in the pure bar-string tensegrity network and nodes on the rigid bodies (those connected to the pure bar-string tensegrity network). Based on the Lagrangian method, the nonlinear statics of the general tensegrity system in terms of the minimal coordinate is first given. Then, we linearize the statics equation and obtain its equivalent form, in terms of the force vector of the compressive and tensile members, to analyze structure equilibrium configurations and prestress modes. To study the system's stability and have a comprehensive insight into the materials and structure members, we present the tangent stiffness matrix as a combination of the structure's prestress, material, and geometric information. It is also shown that without rigid bodies, the governing equations of the general tensegrity system yield to the classical tensegrity structure (pure string-bar network). Form-finding of general tensegrity is implemented based on solving the nonlinear equilibrium equation, where the modification of tangent stiffness matrix and line search algorithm is used. Numerical examples demonstrate the capability of our developed method in finding the feasible prestress modes, conducting form-finding and prestress designs, and checking the structural robustness of any tensegrity systems with rigid bodies.

Lung Cancer Detection using Probabilistic Neural Network with modified Crow-Search Algorithm.

Objective:Lung cancer is a type of malignancy that occurs most commonly among men and the third most common type of malignancy among women. The timely recognition of lung cancer is necessary for decreasing the effect of death rate worldwide. Since the symptoms of lung cancer are identified only at an advanced stage, it is essential to predict the disease at its earlier stage using any medical imaging techniques. This work aims to propose a classification methodology for lung cancer automatically at the initial stage. Methods:The work adopts computed tomography (CT) imaging modality of lungs for the examination and probabilistic neural network (PNN) for the classification task. After pre-processing of the input lung images, feature extraction for the work is carried out based on the Gray-Level Co-Occurrence Matrix (GLCM) and chaotic crow search algorithm (CCSA) based feature selection is proposed.Results:Specificity, Sensitivity, Positive and Negative Predictive Values, Accuracy are the computation metrics used. The results indicate that the CCSA based feature selection effectively provides an accuracy of 90%. Conclusion:The strategy for the selection of appropriate extracted features is employed to improve the efficiency of classification and the work shows that the PNN with CCSA based feature selection gives an improved classification than without using CCSA for feature selection.

An adaptive probabilistic mapping matrix search algorithm for vulnerability analysis of PPS

The paper presents an adaptive probabilistic mapping matrix search algorithm for adversary path planning and vulnerability analysis of physical protection system. The algorithm represents the adversary transition process as stochastic risk-taking path choice behaviors under uncertainties. The interactions among the protective elements are characterized by a full probabilistic mapping scheme of discretized Cell-to-Cell transitions across the area of physical protection for path planning analysis. Practice of the proposed algorithm is demonstrated with a hypothetical case of nuclear facility for risk-significant adversary path identification. The analysis results show that the method is capable of path search analysis for determining the system effectiveness measures.

Exact solutions for the free in-plane vibrations of rectangular plates with arbitrary boundary conditions

Though the free in-plane vibration problem of rectangular plates with classical boundary conditions have been studied using various numerical methods like direct separation of variables, the elastic boundary restraint is more general in the practical structural applications compared with the perfect classical boundary condition. Thus, in this paper, an innovative exact solution on the basis of the method of reverberation ray matrix (MRRM) and golden section search (GSS) algorithm is presented to study the exact free in-plane vibration characteristics of rectangular plates with arbitrary boundary conditions. In the present method, the exact natural frequencies and mode shapes can be very easily obtained when two opposite plate edges have either type of the simply supported boundary conditions and the resting plate edges have the arbitrary boundary conditions including the classical case and general elastic restraints. By the comparison with other published exact solutions, it is shown that the present exact solutions have some obvious advantages which are performed in the excellent accuracy, reliability and efficiency. Performing the study, some of the first-known exact results for the free in-plane vibrations of rectangular plates with elastic boundary restraints are also obtained, which can be worked as the benchmark data for the future approximate methods.

Resource Conflict Resolution Strategy in Collaborative Design Environment

Shortcomings of current conflict resolution methods in solving the problems of disordered competition for design resource in networked design environment are analyzed. By introducing the design structure matrix (DSM) to the planning process of design task, a mathematic description model in collaborative design considering the conflict causes as resource conflict, process conflict and design conflict is given. The reconstruction method of the DSM as well as the DSM based matrix search algorithm is given, based on which the problem of design locking and long waiting because of limited resource in the collaborative design process can be successfully solved. Finally, the design of a bridge crane is used as an example to demonstrate the successful application of the proposed resource conflict resolution strategy in collaborative Design environment.

A computerized and integrated approach for heat exchanger network design in multipurpose batch plants

Significant savings in the utility cost of batch plants can be obtained by heat integration. In this study, an integrated mathematical programming approach is developed for the determination of the cost optimal heat exchanger network for multipurpose batch chemical plants. A single step, interactive computer program (BatcHEN) which is developed for the determination of the campaigns (i.e. the set of products which can be produced simultaneously), the heat exchange areas of all possible heat exchangers in the campaigns and finally the heat exchanger network are all discussed. A matrix search algorithm is used for the determination of the campaigns. Heat exchange areas for the possible heat exchangers are found by solving a nonlinear optimization model with a grid search algorithm. Finally the heat exchanger network optimization is modeled as a mixed integer linear programming problem and then solved by the modeling and optimization software GAMS/XA.