This paper deals with numerical modelling of the residual stress field formed after laser shock peening of a thin blade edge from TC4. It is shown that the application of double-sided symmetric laser shock peening is an effective way of treatment, as it allows to reduce deformation and geometrical changes caused by laser shock peening in comparison with treatment from one side. The results of numerical modelling obtained by varying the machining parameters (power density, spot shape, number of passes, % overlapping) were used to form a database for further training of the neural network. It is shown which machining parameters lead to compressive residual stresses over the entire thickness of the edge, and which ones induce tensile stresses on the surface.

The paper is devoted to the development of the method of laser shock peening (LSP) of metals. To optimize the mode of LSP for Ti-6Al-4V specimens a deep learning model for predicting residual stresses by laser shock peening was developed. A numerical-experimental method was used to carry out the model training, in which an experimental study of the effect of different processing mode on the depth and distribution of residual stresses was carried out. The Johnson-Cook model was used as the governing relationship for modeling the dynamic deformation process. At the second stage, the problem of static equilibrium of a body with a plastically deformed area was numerically solved to determine residual stresses. The results of research on determination of the optimal configuration of the deep learning model showed that when using sinusoidal activation function of the neural network with 4 hidden layers and the number of neurons 10, the best level of accuracy in solving the problem is achieved. The obtained model allows us to optimally determine the LSP mode according to the given limitations of values and depth of residual stresses.

This study is devoted to the investigation of residual stresses distribution (RSD) in a TC4 sample treated with laser shock peening. The study placed special emphasis on analyzing the RSD at the part of the samples structurally similar to a turbine blade, which is more frequently subjected to damage during service according to the aircraft statistics. Results of simulation showed that low power density of 1.11 GWt/cm2 could not induce compressive residual stress on the surface of a treated object. Furthermore, increasing the overlapping of laser spots does not improve the situation and still fail to induce surface compressive residual stress at a laser intensity of 1.11 GWt/cm2. The compressive stresses occur only with the rise in power density. Reducing the spot size from 3 mm to 1 mm for the power density of 10 GWt/cm2 results in a 20% increase in the magnitude of compressive residual stress in the area of interest. Moreover, applying 35% overlapping further enhances this value. In addition to increasing the magnitude of residual stress, this approach also leads to a more homogeneous RSD of the treated material.

Laser shock peening technology allows residual stresses of the first type (according to Davidenkov) to be generated (at a depth of more than 1 mm) in the near-surface zone of products made of metals and alloys. Extensive experimental studies demonstrate that laser shock peening significantly improves their mechanical properties, increases fatigue life, protects against corrosion. However, when applying this technology to products of rather small thickness (e.g., edges of turbine blades, blades of cutting tools) it is necessary to select such parameters of laser pulse impact that will not cause shape change. This paper presents an approach to numerical modelling of the formation of residual stress fields under laser shock treatment when reducing the thickness of products from 3 to 0.35 mm and by varying the magnitude and sequence of laser pulse application. The Johnson-Cook constitutive relation was used for modelling the propagation of elastic-plastic waves. After that, the static calculation of residual stress distribution was performed taking into account the created plastic strain fields. The obtained residual stress fields were compared with each other under different conditions of impact on the workpiece: single-sided treatment; double-sided sequential treatment; double-sided symmetric treatment. Analysis of the calculated stress fields indicated that double-sided symmetric impact is an effective technique for creating a compressive residual stress field in the near-surface zone of products with a thickness of less than 1 mm. At such hardening, it is possible to avoid bending of products and formation of tensile stress fields. It was revealed that, on the one hand, increasing laser intensity (modulo) increases the value of the minimum main residual (compressive) stress in the treatment zone, and, on the other hand, it also increases the maximum main residual (tensile, balancing) stress at a distance from the impact zone.

Additively manufactured materials possess significant heterogeneities and anisotropies of stiffness and strength properties between the growth and transverse directions. Residual stresses induced by the fabrication and processing stages are critical to the service life of these materials. In this work, an experimental study of the residual stress fields was conducted in samples cut from additively manufactured titanium alloy TC4. The depth profiles of residual elastic strains for various regimes of laser impact treatment were obtained on elementary samples in the form of rectangular plates of 100´20´5 mm. Five treatment regimes were studied by varying the laser power density, the spot shape, and the percentage of overlap. The dependence of relief strains and residual stress levels on the laser energy density was obtained for two laser spot shapes: a 1´1 mm square and a 2 mm diameter circle. The numerical model, validated against experimental data for both as-built and laser-peened states, provides a reliable tool for analyzing the residual stresses and strain in additively manufactured components.