United States

Powder-based Laser Metal Deposition (LMD) offers a promising additive manufacturing process given the large number of available materials for cladding or generative applications. In laser cladding of dissimilar materials, it is necessary to control the mixing of substrate and additive in the interaction zone to ensure safe metallurgical bonding whilst avoiding critical chemical compositions that lead to undesired phase precipitation. However, the generation of empirical data for LMD process development is very challenging and time-consuming. In this context, different machine learning models are examined to identify whether they can converge with a small amount of empirical data.&lt;br&gt;
In this work, the prediction accuracy of Back Propagation Neural Network (BPNN), Long Short-Term Memory (LSTM) and eXtreme Gradient Boosting (XGBoost) were compared using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). A hyperparameter optimization was performed for each model. The materials used are 316L as substrate and VDM Alloy 780 as additive. The data set used consists of 40 empirically determined values. The input parameters are laser power, feed rate and powder mass flow rate. The quality characteristics height, width, dilution, Fe-amount and the seam contour are defined as output.&lt;br&gt;
As results, the predictions were compared with retained validation data and described as MSE and MAPE to determine the prediction accuracy for the models. BPNN achieved a prediction accuracy of 0.0072 MSE and 4.37% MAPE and XGBoost of 0.0084 MSE and 6.34% MAPE. The most accurate prediction was achieved by LSTM with 0.0053 MSE and 3.75% MAPE.

ICALEO 2023

Prediction of Clad Quality in Laser Metal Deposition Using Dissimilar Materials: Performance Comparison of Machine Learning-Based Approaches

vdm alloy 780

quality prediction

direct energy deposition

laser metal deposition

machine learning

Powder-based Laser Metal Deposition (LMD) offers a promising additive manufacturing process given the large number of available materials for cladding or generative applications. In laser cladding of dissimilar materials, it is necessary to control the mixing of substrate and additive in the interaction zone to ensure safe metallurgical bonding whilst avoiding critical chemical compositions that lead to undesired phase precipitation. However, the generation of empirical data for LMD process development is very challenging and time-consuming. In this context, different machine learning models are examined to identify whether they can converge with a small amount of empirical data. 
In this work, the prediction accuracy of Back Propagation Neural Network (BPNN), Long Short-Term Memory (LSTM) and eXtreme Gradient Boosting (XGBoost) were compared using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). A hyperparameter optimization was performed for each model. The materials used are 316L as substrate and VDM Alloy 780 as additive. The data set used consists of 40 empirically determined values. The input parameters are laser power, feed rate and powder mass flow rate. The quality characteristics height, width, dilution, Fe-amount and the seam contour are defined as output. 
As results, the predictions were compared with retained validation data and described as MSE and MAPE to determine the prediction accuracy for the models. BPNN achieved a prediction accuracy of 0.0072 MSE and 4.37% MAPE and XGBoost of 0.0084 MSE and 6.34% MAPE. The most accurate prediction was achieved by LSTM with 0.0053 MSE and 3.75% MAPE.

technical paper

**General Chair Welcome**

![](https://assets.underline.io/markdown_image/1/image/d6e6dddc08bf2371b9136ea9c18dc5ab.png)              

Welcome to ICALEO® 2023!
	
We were excited to host the world’s leading international conference on Lasers and Electro-Optics in Chicago. The Laser has been shown to have the potential to revolutionize solutions for major global challenges like energy usage and supply, global warming, and CO2 footprint. Even the fusion energy breakthrough is based on laser technology. The conference, with peer-reviewed scientific and technical presentations, focused on the newest results in Micro Applications, Macro Applications, Additive Manufacturing, Beam Shaping and Frontiers in Laser Applications. Additionally, the Battery-Manufacturing Track gave an overview of the process combined with the newest advances in laser application results. 

The Business Session brought the business aspect and environment of the laser to the audience and the possibility to discuss with seasoned industry leaders from around the world. 

Whether this is the first time you are hearing about ICALEO or you are a longtime attendee, you will find something of interest, new ideas, and an excellent opportunity to network with other laser specialists worldwide. 

**Klaus Löffler **  
ICALEO General Chair   
Managing Director, Precitec GmbH

**What is ICALEO?**

ICALEO® brings together the brightest minds, seasoned professionals, and pioneering researchers from around the world. With a laser-focused agenda, ICALEO offers an exceptional platform to delve into the cutting-edge advancements, diverse applications, and transformative research that define lasers and electro-optics.

Participants will be immersed in a dynamic environment that fosters collaborative learning, networking, and idea exchange. Through engaging plenary presentations, technical sessions, an industry business panel, and networking events, attendees gain insights into the forefront of laser technology. From industrial applications to medical breakthroughs, additive manufacturing to materials processing, ICALEO covers the entire spectrum of laser-related disciplines. Moreover, the event serves as a launching pad for synergistic partnerships, paving the way for professionals to forge connections that shape the future of our industry.

Join us in Chicago and be part of an unparalleled gathering that challenges the boundaries of possibility within lasers and electro-optics. As we convene to share knowledge, explore innovations, and cultivate collaborations, ICALEO stands as a pivotal force driving the evolution of this transformative technology.

**Who attended?**

ICALEO is tailor-made for professionals, researchers, academics, and enthusiasts who are deeply passionate about the world of lasers and electro-optics. If you're an industry trailblazer, an academic luminary, an aspiring expert, or a postgraduate student looking to dive into the latest developments and trends, this is an event you won't want to miss.

Industrial leaders seeking to stay ahead of the curve in their fields, engineers working on laser applications, and manufacturing experts interested in additive manufacturing and materials processing will find ICALEO to be an invaluable platform. Researchers and scientists exploring the forefront of laser technology, from fundamental principles to groundbreaking applications, will also discover a wealth of knowledge and networking opportunities.

Medical professionals investigating laser-based medical advancements, entrepreneurs seeking to innovate with lasers, educators aiming to stay updated with the latest in laser education, and policy makers shaping the industry's landscape are all essential attendees. Whether you're an established expert or a rising star, the 42nd annual ICALEO promises to offer a diverse ecosystem of expertise, connections, and knowledge sharing that caters to the laser and electro-optics communities.

**Fields Represented:**

* Entrepreneurs and Innovators
* Manufacturing Experts
* Students and Graduates
* Policy Makers and Regulators
* Consultants and Advisors
* Technology Enthusiasts
* Suppliers and Manufacturers
* Startups and Innovators
* Researchers in Laser Education

**[View All Proceedings Here](https://icaleo.conferencespot.org/event-data)**

### **Program Tracks & Chairs**

To access the site please register [**here**](https://icaleo.org/attend). 

Please register for the ICALEO 2023 Conference to join the event.

ICALEO® brings together the brightest minds, seasoned professionals, and pioneering researchers from around the world. With a laser-focused agenda, ICALEO offers an exceptional platform to delve into the cutting-edge advancements, diverse applications, and transformative research that define lasers and electro-optics.

Lattice structures in additive manufacturing of 316L stainless steel has gained increasing attention due to their well suited mechanical properties and lightweight characteristics. Infill structures such as honeycomb, lattice, and gyroid have shown promise in achieving desirable mechanical properties for various applications. However, the design process of these structures is complex and time-consuming. In this study, we propose a machine learning-based approach to optimize the design of honeycomb, lattice, and gyroid infill structures in 316L stainless steel fabricated using Laser Powder Bed Fusion (L-PBF) technology under different loading conditions. 
A dataset of simulated lattice structures with varying geometries, wall thickness, distance and angle using a computational model that simulates the mechanical behavior of infill structures under different loading conditions was generated. The dataset was then used to train a machine learning model to predict the mechanical properties of infill structures based on their design parameters. 
Using the trained machine learning model, we then performed a design exploration to identify the optimal infill structure geometry for a given set of mechanical requirements and loading conditions. 
Finally, we fabricated the optimized infill structures using L-PBF technology and conducted a series of mechanical tests to validate their performance under different loading conditions. 
Overall, our study demonstrates the potential of machine learning-based approaches for the efficient and effective design of honeycomb, lattice, and gyroid infill structures in 316L stainless steel fabricated using L-PBF technology under different loading conditions. Furthermore, this approach can be used for dynamic loading studies of infill structures.

Predictive Modeling of Lattice Structure Design for 316L Stainless Steel Using Machine Learning in the L-PBF Process

Powder bed fusion of metals using laser beam (PBF‑LB/M) is a commonly used additive manufacturing process for the production of high-performance metal parts. AlSi10Mg is a widely used material in PBF-LB/M due to its excellent mechanical and thermal properties. However, the part quality of AlSi10Mg parts produced using PBF-LB/M can vary significantly depending on the process parameters. This study investigates the use of machine learning (ML) algorithms for the prediction of the resulting part density of AlSi10Mg parts produced using PBF-LB/M. An empirical dataset of PBF-LB/M process parameters and resulting part densities is used to train a ML models. Furthermore, a methodology is developed to allow density predictions based on simulated meltpool dimensions for different process parameters. This approach uses finite element simulations to calculate the meltpool dimensions, which are then used as input parameters for the ML models. The accuracy of this methodology is evaluated by comparing the predicted densities with experimental measurements. The results show that ML models can accurately predict the part density of AlSi10Mg parts produced using PBF-LB/M. Moreover, the methodology based on simulated meltpool dimensions can provide accurate predictions while significantly reducing the experimental effort needed in process development in PBF-LB/M. This study provides insights into the development of data-driven approaches for the optimization of PBF-LB/M process parameters and the prediction of part properties.

Data-Driven Density Prediction of AlSi10Mg Parts Produced by Laser Powder Bed Fusion Using Machine Learning and Finite Element Simulation

In aerospace, thermal applications demand compact, lightweight and efficient heat exchangers. Additive manufacturing processes offer the potential to create highly complex structures that are not achievable through traditional manufacturing methods. This work presents the development of an additively manufactured fluid-fluid heat exchanger that enhances performance, reduces weight and increases compactness compared to a conventional plate heat exchanger. A numerical model of the conventional plate heat exchanger was created, and fluid dynamics simulations with heat transfer were performed. Verification of the simulations was done by experiments. Then a novel heat exchanger was designed using a bottom-up approach and investigated at different levels of complexity using computational fluid dynamics. The internal structure of the final heat exchanger consists of a repeating triple-periodic Schwarz diamond minimum surface elongated in the direction of flow. The heat exchanger was manufactured in the laser powder bed fusion process in AlSi10Mg. It had a 108% higher compactness and 54% lower weight compared to the plate heat exchanger. Numerical analysis yielded the pressure loss was reduced by 50 to 59% while heat transfer was improved by 3 to 5%. Simulation results were validated by experimental assessment of the novel additively manufactured heat exchanger. Further investigations can be conducted to increase compactness and heat transfer by analyzing the minimum partition wall thickness and the impact of wall roughness and deposit formation.

Design and Assessment of an Additively Manufactured Schwarz Diamond Triply Periodic Minimal Surface Fluid-Fluid Heat Exchanger

Nowadays the technologies have to be more efficient, propose cutting edge processes, be more versatile while being environmental friendly. In this presentation, LASEA will introduce how the beam-shaping can improve the laser processes in particular in microfluidics, aeronautics, photovoltaic applications but also how the beam shaping is expected to increase the productivity of the machine in roller applications, roll-to-roll or batch-to-batch applications. 
Different technologies can be used to shape the laser beam as spatial light modulator (SLM), double SLM, diffractive optical element (DOE) or as well multi-plane light conversion (MPLC) to produce versatile shaped beam (square, round, triangular, specific shape…) or multiple beams (line of beams, matrix of beams,…). The direct laser interference patterning (DLIP) is also a technology that shapes the beam enabling the production of multi-scales processes; micrometric and sub-micrometric structures. Consequently, LASEA will present these different possibilities, their expected impacts and how to integrate them in a laser machine to achieve high throughputs processes. 
Moreover, the beam-shaping leading to multiple beams introduces many challenges in terms of laser machine design and laser development. Indeed, when the number of beams increases the laser has to be more powerful. During this presentation, LASEA will also expose the challenges to manage multiple beams and powerful laser source. Finally, the impacts and improvements expected by these types of technologies will also be present.

Laser Beam Shaping in the Industry

Beam shaping has become increasingly important for laser-based processing, enabling improved efficiency, quality, and precision in a wide range of applications. In this paper, we discuss the challenges of characterizing and defining the appropriate criteria to evaluate a shaped beam for laser material processing applications. 
Beam shaping is essential for many continuous wave (CW) processes, such as high-quality welding of copper and aluminum for e-mobility applications. Similarly, beam shaping is crucial for pulsed applications, particularly surface texturing, enabling precise control of the laser's energy distribution and enhancing the process's quality and scalability. 
We explore various beam shaping technologies, including Diffractive Optical Elements, Refractive Optics, Shaping via Double Core Fiber Laser, Coherent Beam Combining, and Multi-Plane Light Conversion, describing their advantages and limitations. Since these technologies manipulate beams differently, their use can significantly impact the process's outcome. 
We propose various criteria to evaluate the performance of a shaped beam for laser material processing, such as efficiency, uniformity, sharpness, robustness to instabilities, and depth of field. These criteria are critical in defining a good beam for a specific process, ensuring a reliable and repeatable process outcome. 
In conclusion, this paper highlights the importance of proper characterization and evaluation of shaped beams for laser material processing applications. With the appropriate criteria, manufacturers and researchers can optimize the laser's performance and enhance the quality, efficiency, and scalability of laser-based processes.

Defining the Right Criteria to Characterize a Shaped Beam for Laser Material Processing Applications

On-the-fly evaluation and process control of laser surface microprocessing can be realized with the detection of infrared (IR) thermal radiation. In this study, a new multi-focus mirror was developed and tested for large-area detection of IR-thermal radiation during ultrashort pulsed laser surface micromachining. The IR-thermal detection in the laser micromachining was for the first time combined with a fast hardware signal analysis and laser power control using a field programmable gate array (FPGA) module. The new mirror has a long-line distribution of focused points on one side to collect the emitted thermal radiation along a laser scanning line and focuses the captured IR-thermal radiation to a point on the other side for signal analysis. The length of the detection line of the developed multi-focus mirror was 120 mm and it can be expanded up to tens of centimeters. This IR-thermal radiation signal is processed by the FPGA module with a fast evaluation of heat accumulation at a cycle time loop of 50 ns and on-the-fly control of the laser power during surface microprocessing. When the detected heat accumulation signal grows higher than the required value, then the average laser power is automatically decreased, and vice versa. This lR-thermal tracking system was applied for laser surface micromachining of metals and ceramics with polygon- and galvo-scanners. The presented lR-thermal tracking system with the multi-focus mirror can be used also in other applications, such as beam shaping, line scanning spectroscopy, linear surface irradiation, or non-destructive testing (IR-NDT).

Fast IR-Thermal Tracking of Laser Microprocessing with Multi-focus Mirror

Modern beam sources and system technology allows to adjust a large number of parameters relevant to the machining process, and often these parameters can even be varied as a function of time. In principle, a large parameter space makes it possible to find and use particularly well-suited parameter regimes for the specific application, but this generally increases the experimental effort considerably. The efficient optimization of process parameters, incorporating all the possibilities of modern flexible laser beam sources and system technology, in perspective also opens the door to high quality and high throughput. 
Semiconductors as Silicon and Germanium show on the one hand significantly higher ablation efficiencies when they are machined with bursts but then suffers from lower machining quality. On the other hand, especially (100) oriented wafers, can be machined with very low surface roughness due to a melting effect ocuring if a certain peak fluence is exceeded. Combination of these two processes would further exceed the parameter space for a process optimization when high throughput and surface quality is demanded. We will demonstrate the potential of machine learning to significantly shorten the demanded time and effort for the process optimization when these materials are machined with ultra-short laser pulses.

Optimizing the Ultra-Short-Pulsed Laser Machining of Silicon and Germanium With Machine Learning for Highest Throughput and Quality

Industrially widespread laser processes such as laser cutting and laser welding are nowadays usually only monitored and at best controlled in partial areas such as process aborts. On the other hand, process data can be obtained with the aid of acoustic and optical sensors as well as thermal cameras and then processed further. Process data obtained in this way are linked to quality characteristics such as burr formation and edge roughness in cutting and structure depth and spacing in micro structuring on the one hand, and to process parameters such as laser power, feed rate, focus size and position on the other. A prerequisite for controlled laser processes is whether AI-supported algorithms can be used to make reliable predictions about the expected process result based on the process data. Within an internal Fraunhofer project "AI Beam", large amounts of data originating from cutting and welding are used to train an AI (and the correct selection of the appropriate mathematical method) and linked to quality criteria. First results of this project related to cutting will be presented. In another research project, similar approaches for laser micro structuring are being pursued together with industrial partners. Results from this ongoing project will also be presented.

Use of AI for Laser Cutting and Structuring

Laser heat treatment is a process that changes the strength and hardness of the material. Unlike general heat treatment processes, laser heat treatment has the advantage of being able to apply heat locally and having a fast-cooling time. However, due to the high-intensity heat source, excessive heat can be applied to the material, resulting in surface melting, and softening. In this study, a deep learning model based on generative adversarial network was applied to predict the hardening and softening phenomena that occur during laser heat treatment of AH36 carbon steel. As input data, the temperature field of the cross-section, which is obtained by solving the 3-D heat conduction equation using COMSOL, was applied. The input data consist of two temperature distributions: one obtained when the surface temperature is at its maximum, and the other obtained after 0.5-second. The hardness and phase distributions of the cross-section used as ground truth were obtained from a 2 kW multi-mode fiber laser experiment. The model trained with only one-temperature field predicted the hardness distributions well, but the prediction of the softened region was inaccurate. On the other hand, in the case of the model trained with two-temperature fields, it showed high prediction accuracy for hardness and phase distributions in both the softened and hardened regions.

Prediction of Hardness and Phase Distributions in Laser Heat Treatment of AH36 Steel Using Deep Learning

In laser cutting, the fundamental role of the gas flow for melt removal and kerf formation is generally accepted. Beyond this vague understanding, however, the underlying physical mechanisms are not yet fully understood. In particular, detailed data concerning the momentum and heat transfer between the gas and melt have seldom been reported. This study addresses the local interactions between the cutting gas and kerf surface (melt film surface) in a fundamental way based on a combined experimental, theoretical, and numerical approach. Typical solid-state laser cut edges are analyzed considering the characteristic surface structures and the basic influences of the gas flow on the global and local melt movement. Here, apparent structures in the micrometer range indicate the effect of vortical gas structures close to the wall. Theoretical investigation of the gas boundary layer is conducted by semi-empirical equations and the transfer of basic results from boundary layer theory. It is shown that the boundary layer is in transition between laminar and turbulent flow, and local flow separations and shock-boundary layer interactions primarily induce spatially periodic and quasi-stationary instability modes. An improved numerical model of the cutting gas flow confirms the theoretical results and exhibits good agreement with experimental cut edges, reproducing the relevant instability modes and quantifying the local momentum and heat transfer distributions between gas and melt. With the knowledge gained about the underlying physical mechanisms, promising approaches for improvements of the fusion cutting performance are proposed.

Downloads

Next from ICALEO 2023

Predictive Modeling of Lattice Structure Design for 316L Stainless Steel Using Machine Learning in the L-PBF Process

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ICALEO 2023

Predictive Modeling of Lattice Structure Design for 316L Stainless Steel Using Machine Learning in the L-PBF Process

Downloads