Search the digital library catalog

Abstract: Optimizing cutting parameters in fiber laser cutting of austenitic stainless steel is challenging due to the complex interplay of multiple variables and quality metrics. To solve this problem, Latin hypercube sampling was used to ensure a comprehensive and efficient exploration of the parameter space with a smaller number of trials (185), coupled with feedforward neural networks for predictive modeling. The networks were trained with a leave-oneout cross-validation strategy to mitigate overfitting. Different configurations of hidden layers, neurons, and training functions were used. The approach was focused on minimizing dross and roughness on both the top and bottom areas of the cut surfaces. During the testing phase, an average MSE of 0.063 and an average MAPE of 4.68% were achieved by the models. Additionally, an experimental test was performed on the best parameter settings predicted by the models. Initial modelling was conducted for each quality metric individually, resulting in an average percentage difference of 1.37% between predicted and actual results. Grid search was also per formed to determine an optimal input parameter set for all outputs, with predictions achieving an average ac curacy of 98.34%. Experimental validation confirmed the accuracy and robustness of the model predictions, demonstrating the effectiveness of the methodology in optimizing multiple parameters of complex laser cutting processes.
Keywords: laser cutting optimization, cut surface quality, dross formation, Latin hypercube sampling, feedforward neural network
Published in DKUM: 10.01.2025; Views: 0; Downloads: 3
Full text (3,38 MB)
This document has many files! More...

Abstract: Machine learning algorithms have been available since the 1990s, but it is much more recently that they have come into use also in the physical sciences. While these algorithms have already proven to be useful in uncovering new properties of materials and in simplifying experimental protocols, their usage in liquid crystals research is still limited. This is surprising because optical imaging techniques are often applied in this line of research, and it is precisely with images that machine learning algorithms have achieved major breakthroughs in recent years. Here we use convolutional neural networks to probe several properties of liquid crystals directly from their optical images and without using manual feature engineering. By optimizing simple architectures, we fnd that convolutional neural networks can predict physical properties of liquid crystals with exceptional accuracy. We show that these deep neural networks identify liquid crystal phases and predict the order parameter of simulated nematic liquid crystals almost perfectly. We also show that convolutional neural networks identify the pitch length of simulated samples of cholesteric liquid crystals and the sample temperature of an experimental liquid crystal with very high precision.
Keywords: liquid crystal, neural network, artificial intelligence, soft matter
Published in DKUM: 20.11.2024; Views: 0; Downloads: 2
Full text (1,94 MB)
This document has many files! More...

Keywords: voltage sag (dip), source localization, supervised and unsupervised learning, convolutional neural network, time-sample-based features
Published in DKUM: 23.08.2024; Views: 65; Downloads: 5
Full text (15,94 MB)

Abstract: PLS-SEM has been used recently more and more often in studies researching critical factors influencing the acceptance and use of information systems, especially when the technology acceptance model (TAM) is implemented. TAM has proved to be the most promising model for researching different viewpoints regarding information technologies, tools/applications, and the acceptance and use of information systems by the employees who act as the end-users in companies. However, the use of advanced PLS-SEM techniques for testing the extended TAM research models for the acceptance of enterprise resource planning (ERP) systems is scarce. The present research aims to fill this gap and aims to show how PLS-SEM results can be enhanced by advanced techniques: artificial neural network analysis (ANN) and Importance–Performance Matrix Analysis (IPMA). ANN was used in this research study to overcome the limitations of PLS-SEM regarding the linear relationships in the model. IPMA was used in evaluating the importance and performance of factors/drivers in the SEM. From the methodological point of view, results show that the research approach with ANN artificial intelligence complements the results of PLS-SEM while allowing the capture of nonlinear relationships between the variables of the model and the determination of the relative importance of each factor studied. On other hand, IPMA enables the identification of factors with relatively low performance but relatively high importance in shaping dependent variables.
Keywords: traditional PLS-SEM, artificial neural network (ANN) analysis, Importance–Performance Matrix Analysis (IPMA), ERP system acceptance, TAM model
Published in DKUM: 09.07.2024; Views: 103; Downloads: 14
Full text (2,52 MB)
This document has many files! More...

Abstract: In cutting processes, tool condition affects the quality of the manufactured parts. As such, an essential component to prevent unplanned downtime and to assure machining quality is having information about the state of the cutting tool. The primary function of it is to alert the operator that the tool has reached or is reaching a level of wear beyond which behaviour is unreliable. In this paper, the tool condition is being monitored by analysing the electric current on the main spindle via an artificial intelligence model utilising an LSTM neural network. In the current study, the tool is monitored while working on a cylindrical raw piece made of AA6013 aluminium alloy with a custom polycrystalline diamond tool for the purposes of monitoring the wear of these tools. Spindle current characteristics were obtained using external measuring equipment to not influence the operation of the machine included in a larger production line. As a novel approach, an artificial intelligence model based on an LSTM neural network is utilised for the analysis of the spindle current obtained during a manufacturing cycle and assessing the tool wear range in real time. The neural network was designed and trained to notice significant characteristics of the captured current signal. The conducted research serves as a proof of concept for the use of an LSTM neural network-based model as a method of monitoring the condition of cutting tools.
Keywords: tool condition monitoring, artificial intelligence, LSTM neural network
Published in DKUM: 22.04.2024; Views: 181; Downloads: 22
Full text (3,75 MB)
This document has many files! More...