• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.741-747
• /
• 2022

Fatigue lowers an individual's ability and makes it difficult to perform work. As fatigue accumulates, concentration decreases and thus the possibility of causing a safety accident increases. Awareness of fatigue is subjective, but it is necessary to quantitatively measure the level of fatigue in the actual field. In previous studies, it was proposed to measure the level of fatigue by expert judgment by adding objective indicators such as bio-signal analysis to subjective evaluations such as multidisciplinary fatigue scales. However this method is difficult to evaluate fatigue in real time in daily life. This paper is a study on the fatigue classification model that determines the fatigue level of workers in real time using speech data recorded in the field. Machine learning models such as logistic classification, support vector machine, and random forest are trained using speech data collected in the field. The performance evaluation showed good performance with accuracy of 0.677 to 0.758, of which logistic classification showed the best performance. From the experimental results, it can be seen that it is possible to classify the fatigue level using speech signals.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.9
• /
• pp.798-804
• /
• 2011

In this paper, optimal spot weld layout design for a shock tower structure is presented. This design increases the fatigue life of the spot-welds thereby increasing the fatigue life of the shock tower itself. In order to predict the fatigue life, a quasi-static analysis has been conducted then a fatigue analysis was performed through the application of random vibration loads. In order to optimize the spot weld layout, the design variables that have an effect on the spot weld fatigue life were determined. A spot weld fatigue analysis was then conducted based on the experiment design. Finally, a response surface model was made using the fatigue analysis results and an optimized spot weld layout model, one that increases the fatigue life of the spot welds and thereby the fatigue life of the shock tower, was developed.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.10
• /
• pp.2475-2482
• /
• 1993

The effects of the hole size(2R) and the specimen width(W) on the fatigue strength and the fatigue life in plain woven glass/epoxy composite plates are experimentally investigated under constant amplitude tensile fatigue loading. It is shown in this study that the notch sensitivity under fatigue loading is lower than that under static loading. It can be explained by the fact that the stress concentration is relaxed by the damage developed at the boundary of circular hole. To predict the fatigue strength at a specific cycle, the modified point stress criterion represented as a function of the geometry of the specimen(2R and W) is applied. It is found that the model used in the prediction of the notched tensile strength predicts the fatigue strength with reasonable accuracy. A model for predicting the fatigue life in the notched specimen, based on the S-$N_f$, curve in the smooth specimen, is suggested.

• Journal of Mechanical Science and Technology
• /
• v.19 no.7
• /
• pp.1393-1404
• /
• 2005

Fatigue crack growth and life have been estimated based on established empirical equations. In this paper, an alternative method using artificial neural network (ANN) -based model developed to predict fatigue damages simultaneously. To learn and generalize the ANN, fatigue crack growth rate and life data were built up using in-plane bending fatigue test results. Single fracture mechanical parameter or nondestructive parameter can't predict fatigue damage accurately but multiple fracture mechanical parameters or nondestructive parameters can. Existing fatigue damage modeling used this merit but limited real-time damage monitoring. Therefore, this study shows fatigue damage model using backpropagation neural networks on the basis of X -ray half breadth ratio B / $B_o$, fractal dimension $D_f$ and fracture mechanical parameters can estimate fatigue crack growth rate da/ dN and cycle ratio N / $N_f$ at the same time within engineering limit error ($5\%$).

• Journal of Ocean Engineering and Technology
• /
• v.30 no.5
• /
• pp.341-348
• /
• 2016

The fatigue damage caused by wide band loadings has generally been predicted using fatigue damage models in the frequency domain rather than a rain-flow counting method in the time domain because of its computation cost. This study showed that these fatigue damage models can be simplified in the form of normalized fatigue damage as a function of the S-N curve slope and bandwidth parameters. Based on numerical simulations of various wide band spectra, it was found that fatigue damage models in the form of normalized fatigue damage with one S-N curve slope and two bandwidth parameters( α₁ , α₂ ) provided less reasonable fatigue damage. Therefore, an additional bandwidth parameter needs to be considered based on a sensitivity study using various neural networks, which proved that α_1-5 would be the dominant factor of a fatigue damage model as an additional bandwidth parameter.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.13 no.5
• /
• pp.116-122
• /
• 2014

In this study, 2 kinds of twist run models as exercise equipments are compared by durability analyses of fatigue and vibration. Maximum equivalent stresses are shown as 3.3 MPa and 16.6 MPa at the parts of stress concentrations at models 1 and 2. As the values becomes much lower than yield stress of this models, these models are shown to be safe designs. Model 1 becomes stronger than model 2 at natural frequency analysis. Fatigue lives become lowest at four axis parts and one axis part respectively in cases of models 1 and 2. Maximum damage probability at fatigue is shown to be 2.4% near the average stress of 0 in case of model 1 but this probability becomes 0.6 % in case of model 2. Model 1 has the maximum damage possibility 4 times more than model 2 at these states. As the result of this study is applied by the design of twist run, the prevention on fatigue damage and the durability are predicted.

• Journal of the Society of Naval Architects of Korea
• /
• v.49 no.4
• /
• pp.359-366
• /
• 2012

This is the final one of the two companion papers dealing with accuracy of accumulated fatigue damage estimation under wide band process. It is stated that four kinds of wide band models exist: typed of equivalent stress, combined PDF, correction factor, and damage combination. For the idealized ESDs from full scale measurement data on an 8100TEU container vessel, fatigue damages are compared for a narrow band prediction model based on Rayleigh PDF and five wide band fatigue prediction models of Dirlik, Wirsching-Light, Jiao-Moan, Benasciutti and DNV. DNV model consistently overestimates fatigue damages regardless of variation of ESDs. Predictions by Jiao-Moan model, which is understood as standard method for design of offshore platforms, are also in conservative side. Best accuracy is found from the results by Dirlik and Benasciutti models, but Benasciutti model is preferred since it can easily combined with narrow band fatigue damage based on Rayleigh PDF.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.10a
• /
• pp.259-262
• /
• 2009

The influence of pre-strain in low-cycle fatigue behavior of Fe-18Mn-0.05Al-0.6C TWIP steel was studied by conducting axial strain-controlled tests. As-received plates were deformed by rolling with reduction ratios of 10 and 30%, respectively. A triangular waveform with a constant frequency of 1 Hz was employed for low cycle fatigue test at the strain amplitudes in the range of ${\pm}0.4{\sim}{\pm}0.6$ pct. The results showed that low-cycle fatigue life was strongly dependent on the amount of pre-strain as well as the strain amplitude. Increasing the amount of prestrain, the number of reversals to failure was significantly decreased at high strain amplitudes, but the effect was negilgible at low strain amplitudes. A new model for predicting fatigue life of pre-strained body has been devised adding a correction term of ${\Delta}E_{pre-strain}$ to the energy-based fatigue damage parameter.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.12 s.255
• /
• pp.1534-1542
• /
• 2006

In this paper, the concept of accelerated life test, which is a popular research field nowadays, is applied to the shot peened material. To predict the efficient and exact room temperature fatigue characteristics from the high temperature fatigue data, the adequate accelerated model is investigated. Ono type rotary bending fatigue tester and high temperature chamber were used for the experiment. Room temperature fatigue lives were predicted by applying accelerated models and doing reliability evaluation. Room temperature fatigue tests were accomplished to check the effectiveness of predicted data and the adequate accelerated life test models were presented by considering errors. Experimental result using Arrhenius model, fatigue limit obtain almost 5.45% of error, inverse power law has about 1.36% of error, so we found that inverse power law is applied well to temperature-life relative of shot peened material.

• Journal of Ocean Engineering and Technology
• /
• v.26 no.2
• /
• pp.26-32
• /
• 2012

In this paper, the effects of irregular bead shapes on fatigue life were investigated. A modified S-N curve method was used to estimate the fatigue life, which considered the inherent multiaxiality caused by the geometrical feature produced by the welding process. The point method of the critical distance method was used to determine the fatigue effective stress. Three types of fillet joint models were tested in the fatigue experiments. For each model, real bead shapes were collected using a 3D laser scanner, and finite element analyses were performed. The results of the analyses with actual bead shapes were compared with those using an idealized bead shape model. The results of the present analytical methods showed good agreement with the experimental results.