Predictive capabilities for laser machining via a neural network

Real-time acoustic monitoring of laser paint removal based on deep learning

The acoustic signals generated during the laser paint removal process contain valuable information that reflects the state of paint removal. However, it is often overshadowed by complex environmental noise, posing significant challenges for real-time monitoring of paint removal based on acoustic signals. This paper introduces a real-time acoustic monitoring method for laser paint removal using deep learning techniques for the first time. Initially, the original acoustic signals from both clean and unclean paint removal processes are collected and denoised to extract time-domain, frequency-domain, and time-frequency-domain features. The mel frequency cepstral coefficients (MFCC) from the time-frequency domain are then used as inputs to train a convolutional neural network (CNN). The trained CNN model achieves a real-time discrimination accuracy of 97% and an AUC-ROC score of 99%, outperforming classical deep learning models of back propagation neural network (BP), support vector machine (SVM), and recurrent feedforward neural network (RF) that use time and frequency domain features as input. Furthermore, a real-time paint removal monitoring system based on this CNN model was developed, utilizing the NVIDIA Jetson Nano as the core controller. The system demonstrated continuous monitoring capabilities over a period of 1 hour, with a single judgment time of about 60 ms and an accuracy of 94.3%, thereby achieving real-time online monitoring.

Prediction of Femtosecond Laser Etching Parameters Based on a Backpropagation Neural Network with Grey Wolf Optimization Algorithm

Investigating the optimal laser processing parameters for industrial purposes can be time-consuming. Moreover, an exact analytic model for this purpose has not yet been developed due to the complex mechanisms of laser processing. The main goal of this study was the development of a backpropagation neural network (BPNN) with a grey wolf optimization (GWO) algorithm for the quick and accurate prediction of multi-input laser etching parameters (energy, scanning velocity, and number of exposures) and multioutput surface characteristics (depth and width), as well as to assist engineers by reducing the time and energy require for the optimization process. The Keras application programming interface (API) Python library was used to develop a GWO-BPNN model for predictions of laser etching parameters. The experimental data were obtained by adopting a 30 W laser source. The GWO-BPNN model was trained and validated on experimental data including the laser processing parameters and the etching characterization results. The R2 score, mean absolute error (MAE), and mean squared error (MSE) were examined to evaluate the prediction precision of the model. The results showed that the GWO-BPNN model exhibited excellent accuracy in predicting all properties, with an R2 value higher than 0.90.

Recent progress and treatment strategy of pectin polysaccharide based tissue engineering scaffolds in cancer therapy, wound healing and cartilage regeneration

Natural polymers and its mixtures in the form of films, sponges and hydrogels are playing a major role in tissue engineering and regenerative medicine. Hydrogels have been extensively investigated as standalone materials for drug delivery purposes as they enable effective encapsulation and sustained release of drugs. Biopolymers are widely utilised in the fabrication of hydrogels due to their safety, biocompatibility, low toxicity, and regulated breakdown by human enzymes. Among all the biopolymers, polysaccharide-based polymer is well suited to overcome the limitations of traditional wound dressing materials. Pectin is a polysaccharide which can be extracted from different plant sources and is used in various pharmaceutical and biomedical applications including cartilage regeneration. Pectin itself cannot be employed as scaffolds for tissue engineering since it decomposes quickly. This article discusses recent research and developments on pectin polysaccharide, including its types, origins, applications, and potential demands for use in AI-mediated scaffolds. It also covers the materials-design process, strategy for implementation to material selection and fabrication methods for evaluation. Finally, we discuss unmet requirements and current obstacles in the development of optimal materials for wound healing and bone-tissue regeneration, as well as emerging strategies in the field.

Prediction of the superimposed laser shot number for copper using a deep convolutional neural network

Image-based deep learning (IBDL) is an advanced technique for predicting the surface irradiation conditions of laser surface processing technology. In pulsed-laser surface processing techniques, the number of superimposed laser shots is one of the fundamental and essential parameters that should be optimized for each material. Our primary research aims to build an adequate dataset using laser-irradiated surface images and to successfully predict the number of superimposed shots using the pre-trained deep convolutional neural network (CNN) models. First, the laser shot experiments were performed on copper targets using a nanosecond YAG laser with a wavelength of 532 nm. Then, the training data were obtained with the different superimposed shots of 1 to 1024 in powers of 2. After that, we used several pre-trained deep CNN models to predict the number of superimposed laser shots. Based on the dataset with 1936 images, VGG16 shows a high validation accuracy, higher sensitivity, and more than 99% precision than other deep CNN models. Utilizing the VGG16 model with high sensitivity could positively impact the industries' time, efficiency, and overall production.

Deep-Learning-Assisted Focused Ion Beam Nanofabrication

Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.

Ultrafast laser ablation simulator using deep neural networks

Laser-based material removal, or ablation, using ultrafast pulses enables precision micro-scale processing of almost any material for a wide range of applications and is likely to play a pivotal role in providing mass customization capabilities in future manufacturing. However, optimization of the processing parameters can currently take several weeks because of the absence of an appropriate simulator. The difficulties in realizing such a simulator lie in the multi-scale nature of the relevant processes and the high nonlinearity and irreversibility of these processes, which can differ substantially depending on the target material. Here we show that an ultrafast laser ablation simulator can be realized using deep neural networks. The simulator can calculate the three-dimensional structure after irradiation by multiple laser pulses at arbitrary positions and with arbitrary pulse energies, and we applied the simulator to a variety of materials, including dielectrics, semiconductors, and an organic polymer. The simulator successfully predicted their depth profiles after irradiation by a number of pulses, even though the neural networks were trained using single-shot datasets. Our results indicate that deep neural networks trained with single-shot experiments are able to address physics with irreversibility and chaoticity that cannot be accessed using conventional repetitive experiments.

Single step phase optimisation for coherent beam combination using deep learning

Coherent beam combination of multiple fibres can be used to overcome limitations such as the power handling capability of single fibre configurations. In such a scheme, the focal intensity profile is critically dependent upon the relative phase of each fibre and so precise control over the phase of each fibre channel is essential. Determining the required phase compensations from the focal intensity profile alone (as measured via a camera) is extremely challenging with a large number of fibres as the phase information is obfuscated. Whilst iterative methods exist for phase retrieval, in practice, due to phase noise within a fibre laser amplification system, a single step process with computational time on the scale of milliseconds is needed. Here, we show how a neural network can be used to identify the phases of each fibre from the focal intensity profile, in a single step of ~ 10 ms, for a simulated 3-ring hexagonal close-packed arrangement, containing 19 separate fibres and subsequently how this enables bespoke beam shaping. In addition, we show that deep learning can be used to determine whether a desired intensity profile is physically possible within the simulation. This, coupled with the demonstrated resilience against simulated experimental noise, indicates a strong potential for the application of deep learning for coherent beam combination.

Modelling of fibre laser cutting via deep learning

Laser cutting is a materials processing technique used throughout academia and industry. However, defects such as striations can be formed while cutting, which can negatively affect the final quality of the cut. As the light-matter interactions that occur during laser machining are highly non-linear and difficult to model mathematically, there is interest in developing novel simulation methods for studying these interactions. Deep learning enables a data-driven approach to the modelling of complex systems. Here, we show that deep learning can be used to determine the scanning speed used for laser cutting, directly from microscope images of the cut surface. Furthermore, we demonstrate that a trained neural network can generate realistic predictions of the visual appearance of the laser cut surface, and hence can be used as a predictive visualisation tool.

The future of bone regeneration: integrating AI into tissue engineering

Tissue engineering is a branch of regenerative medicine that harnesses biomaterial and stem cell research to utilise the body's natural healing responses to regenerate tissue and organs. There remain many unanswered questions in tissue engineering, with optimal biomaterial designs still to be developed and a lack of adequate stem cell knowledge limiting successful application. Advances in artificial intelligence (AI), and deep learning specifically, offer the potential to improve both scientific understanding and clinical outcomes in regenerative medicine. With enhanced perception of how to integrate artificial intelligence into current research and clinical practice, AI offers an invaluable tool to improve patient outcome.

Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environments

Reinforcement learning was carried out in a simulated environment to learn continuous velocity control over multiple motor axes. This was then applied to a real-world optical tweezers experiment with the objective of moving a laser-trapped microsphere to a target location whilst avoiding collisions with other free-moving microspheres. The concept of training a neural network in a virtual environment has significant potential in the application of machine learning for experimental optimization and control, as the neural network can discover optimal methods for problem solving without the risk of damage to equipment, and at a speed not limited by movement in the physical environment. As the neural network treats both virtual and physical environments equivalently, we show that the network can also be applied to an augmented environment, where a virtual environment is combined with the physical environment. This technique may have the potential to unlock capabilities associated with mixed and augmented reality, such as enforcing safety limits for machine motion or as a method of inputting observations from additional sensors.

Modelling laser machining of nickel with spatially shaped three pulse sequences using deep learning

Femtosecond laser machining is a complex process, owing to the high peak intensities involved. Modelling approaches for the prediction of final sample quality based on photon-atom interactions are therefore challenging to extrapolate up to the microscale and beyond. The problem is compounded when multiple exposures are used to produce a final structure, where surface modifications from previous exposures must be taken into consideration. Neural network approaches allow for the automatic creation of a model that accounts for these challenging processes, without any physical knowledge of the processes being programmed by a specialist. We present such a network for the prediction of surface quality for multi-exposure femtosecond machining on a 5µm electroless nickel layer deposited on copper, where each pulse is uniquely spatially shaped using a spatial light modulator. This neural network modelling method accurately predicts the surface profile after three, sequential, overlapping exposures of dissimilar intensity patterns. It successfully reproduces such effects as the sub-diffraction limit machining feasible with multiple exposures, and the smoothing effect on edge-burr from previous exposures expected in multi-exposure laser machining.

Real-time particle pollution sensing using machine learning

Particle pollution is a global health challenge that is linked to around three million premature deaths per year. There is therefore great interest in the development of sensors capable of precisely quantifying both the number and type of particles. Here, we demonstrate an approach that leverages machine learning in order to identify particulates directly from their scattering patterns. We show the capability for producing a 2D sample map of spherical particles present on a coverslip, and also demonstrate real-time identification of a range of particles including those from diesel combustion.