Search results for "Mach"
showing 10 items of 3360 documents
Experimental Research on the Cutting of Metal Materials by Electrical Discharge Machining with Contact Breaking with Metal Band as Transfer Object
2020
The scientific paper presents practical research carried out by a mixed team of Romanian researchers from universities and the business environment. The research consists in applying the process of cutting metallic materials through electrical discharge machining with contact breaking using a metal band as a transfer object. The research was implemented with the help of a specially designed installation in the laboratory and subsequently all the necessary steps were taken to obtain the patent for it. Various metallic materials were cut using this process, but first of all, high alloy steels. In the global research conducted by the authors, active experimental programs and classic experiment…
Assembly Process Modeling Through Long Short-Term Memory
2021
This paper studies Long Short-Term Memory as a component of an adaptive assembly assistance system suggesting the next manufacturing step. The final goal is an assistive system able to help the inexperienced workers in their training stage or even experienced workers who prefer such support in their manufacturing activity. In contrast with the earlier analyzed context-based techniques, Long Short-Term Memory can be applied in unknown scenarios. The evaluation was performed on the data collected previously in an experiment with 68 participants assembling as target product a customizable modular tablet. We are interested in identifying the most accurate method of next assembly step prediction…
Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm
2018
Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process for determining synaptic weights of such neural networks can be computationally very expensive. In this paper we propose a new learning algorithm for learning the synaptic weights of the single hidden layer feedforward neural networks in order to reduce the learning time. We propose combining the upgraded bat algorithm with the extreme learning machine. The proposed approach reduces the number of evaluations needed to train a neural network and efficiently finds optimal input weights and the hidden biases. The proposed algorithm was tested on standard benchmark clas…
Linearized Piecewise Affine in Control and States Hydraulic System: Modeling and Identification
2018
In this paper, the modeling and identification of a nonlinear actuated hydraulic system is addressed. The full-order model is first reduced in relation to the load pressure and flow dynamics and, based thereupon, linearized over the entire operational state-space. The dynamics of the proportional control valve is identified, analyzed, and intentionally excluded from the reduced model, due to a unity gain behavior in the frequency range of interest. The input saturation and dead-zone nonlinearities are considered while the latter is identified to be close to 10% of the valve opening. The mechanical part includes the Stribeck friction detected and estimated from the experiments. The lineariza…
A proposed mapping method for aligning machine execution data to numerical control code
2019
The visions of the digital thread and smart manufacturing have boosted the potential of relating downstream data to upstream decisions in design. However, to date, the tools and methods to robustly map across the related data representations is significantly lacking. In response, we propose a mapping technique for standard manufacturing data representations. Specifically, we focus on relating controller data from machining tools in the form of MTConnect, an emerging standard that defines the vocabulary and semantics as well as communications protocols for execution data, and G-Code, the most widely used standard for numerical control (NC) instructions. We evaluate the efficacy of our mappin…
Adjusted bat algorithm for tuning of support vector machine parameters
2016
Support vector machines are powerful and often used technique of supervised learning applied to classification. Quality of the constructed classifier can be improved by appropriate selection of the learning parameters. These parameters are often tuned using grid search with relatively large step. This optimization process can be done computationally more efficiently and more precisely using stochastic search metaheuristics. In this paper we propose adjusted bat algorithm for support vector machines parameter optimization and show that compared to the grid search it leads to a better classifier. We tested our approach on standard set of benchmark data sets from UCI machine learning repositor…
An insight into the electrical energy demand of friction stir welding processes: the role of process parameters, material and machine tool architectu…
2018
The manufacturing sector accounts for a high share of global electrical energy consumption and CO 2 emissions, and therefore, the environmental impact of production processes is being more and more investigated. An analysis of power and energy consumption in friction stir welding processes can contribute to the characterization of the process from a new point of view and also provide useful information about the environmental impact of the process. An in-depth analysis of electrical energy demand of friction stir welding is here proposed. Different machine tool architectures, including an industrial dedicated machine, have been used to weld aluminum and steel sheets under different process …
Design and Calibration of a Specialized Polydioptric Camera Rig
2017
International audience; It has been observed in the nature that all creatures have evolved highly exclusive sensory organs depending on their habitat and the form of resources availability for their survival. In this project, a novel omnidirectional camera rig, inspired from natural vision sensors, is proposed. It is exclusively designed to operate for highly specified tasks in the field of mobile robotics. Navigation problems on uneven terrains and detection of the moving objects while the robot is itself in motion are the core problems that omnidirectional systems tackle. The proposed omnidirectional system is a compact and a rigid vision system with dioptric cameras that provide a 360° f…
MFNet: Multi-feature convolutional neural network for high-density crowd counting
2020
The crowd counting task involves the issue of security, so now more and more people are concerned about it. At present, the most difficult problem of population counting consists in: how to make the model distinguish human head features more finely in the densely populated area, such as head overlap and how to find a small-scale local head feature in an image with a wide range of population density. Facing these challenges, we propose a network for multiple feature convolutional neural network, which is called MFNet. It aims to get high-quality density maps in the high-density crowd scene, and at the same time to perform the task of the count and estimation of the crowd. In terms of crowd c…
Do Randomized Algorithms Improve the Efficiency of Minimal Learning Machine?
2020
Minimal Learning Machine (MLM) is a recently popularized supervised learning method, which is composed of distance-regression and multilateration steps. The computational complexity of MLM is dominated by the solution of an ordinary least-squares problem. Several different solvers can be applied to the resulting linear problem. In this paper, a thorough comparison of possible and recently proposed, especially randomized, algorithms is carried out for this problem with a representative set of regression datasets. In addition, we compare MLM with shallow and deep feedforward neural network models and study the effects of the number of observations and the number of features with a special dat…