Modeling Of Manufacturing Processes Research Articles

Three-dimensional physical modeling of the wet manufacturing process of solid-state battery electrodes

Poor design of composite electrodes in Solid-State Batteries (SSBs) is one of the main reasons for their low performance. Although modeling techniques offer great potential in investigating multiple conditions for microstructure optimization, SSB manufacturing remains almost unaddressed in terms of computational studies. We present here a three-dimensional physics-based modeling workflow to investigate the impact of wet manufacturing process parameters on the properties of SSB tape casted composite electrodes based on LiNi0.6Mn0.2Co0.2O2 as the active material and Li6PSCl5 sulfide solid electrolyte. Our proposed workflow models the entire process of wet manufacturing of SSB electrodes, starting with the slurry consisting of active material, carbon additive, binder, solid electrolyte and solvent, and continues through its drying process, and the calendering of the resulting electrodes. Our focus is in particular on the impact of the calendering degree on the microstructure of the electrode. We characterize the resulting microstructures in terms of electronic and ionic conduction properties. We believe that this first-of-its-kind wet manufacturing process model for SSB cathodes is an important step towards the development of systematic modeling approaches that can provide practical optimization of the interfaces between materials in electrodes to improve SSB performance and durability.

An innovative teaching model of automotive manufacturing process based on ADDIE model

Abstract The teaching mode of the innovative automotive manufacturing process is to improve students’ automotive manufacturing technology. In this paper, firstly, the basic principle of the ant colony algorithm is introduced, and the ant colony algorithm is improved and optimized by heuristic function, state transfer probability and pheromone update rule. Then the optimized ant colony algorithm is used as the base algorithm for constructing the ADDIE model. After establishing the ADDIE model, two dimensional indicators of the teaching mode of the automotive manufacturing process, i.e. teaching objectives of the basic course and application course, are mined for the example of the automotive manufacturing process course of L school. The two example indicators proposed are analyzed and illustrated using the example data. Regarding the basic course teaching objectives, the mean values of A, B, C and D evaluation indicators accounted for 47.73%, 21.46%, 20.17% and 10.65%, respectively. Regarding the teaching objectives of the application courses, the mean values of the four evaluation indexes of A, B, C and D account for 50.24%, 15.75%, 21.05% and 12.96%, respectively. The innovative teaching mode of the automotive manufacturing process based on the ADDIE model is beneficial for students to learn technology in a new way and also for delivering high-quality technical talents to automotive manufacturing enterprises.

Discrete element modeling of selective laser sintering additive manufacturing processes

This work presents a simple methodology for the simulation of selective laser sintering processes in advanced manufacturing. Our approach is based on the Discrete Element Method (DEM) to represent the powder bed, combined with lumped heat transfer equations to describe the various thermal phenomena that may take place for thermo-mechanically-active particles forming discrete particle systems. Phase transformation, which may be critical in this type of application, is also considered. Numerical examples are provided to illustrate the practical use of the methodology.

Modeling product carbon footprint for manufacturing process

To reduce carbon intensity and improve energy efficiency in product manufacturing, a comprehensive carbon emission model is essential. Most of the existing researches focus on specific aspects of part machining and lack a quantitative model of the product manufacturing process. Therefore, this paper decomposes and evolves the carbon footprint of product manufacturing from the workshop layer, forming a systematic carbon emission quantitative model. The product manufacturing process is divided into manufacturing equipment layer, part layer, product layer and workshop layer. The sources of carbon emissions in each layer are analyzed and modeled. Finally, take a certain type of wind turbine gearbox as an example. The carbon emissions model for manufacturing process of wind turbine gearbox is established, which provides directions for carbon emission reduction of related manufacturing enterprises. The results show that the rear housing, front housing, and 1st plant carrier are the main carbon emission parts of wind turbine gearbox.

Enhancing the Predictive Capabilities of Microstructure Simulations of PBF-LB/M by an Evaluation of Nucleation Theories

Powder Bed Fusion of Metals using a Laser Beam (PBF-LB/M) has proven to be a competitive manufacturing technology to produce customized parts with a high geometric complexity. Due to process-specific characteristics, such as high cooling rates, the microstructural features can be tailored. This offers the possibility to locally control the mechanical properties. Therefore, the grain structure has to be reliably predicted at first. The starting point of the grain formation and the growth process is characterized by the nucleation. Over the course of this study, various nucleation theories were applied to the PBF-LB/M process and their suitability was evaluated. The two Sc-modified aluminum alloys Scalmalloy® and Scancromal® were processed with a novel experimental PBF-LB/M setup. By performing melt pool simulations based on the Finite Element Method (FEM), the input data for the nucleation models were obtained. The simulatively predicted nucleation zones based on the different theories were compared to real metallographic images and to literature results. It was found that the phenomenological approach should be used whenever no first-time-right prediction of the simulation is necessary. The physically based models with the heterogeneous nucleation should be applied if a first-time-right prediction is striven for. For applications in PBF-LB/M, the nucleation models should be extended in terms of the influence of precipitates and the high cooling rates during the manufacturing process. The presented approach may be used to further assess grain nucleation models for various additive manufacturing processes.

A Generalized Framework for Adopting Regression-Based Predictive Modeling in Manufacturing Environments

In this paper, the growing significance of data analysis in manufacturing environments is exemplified through a review of relevant literature and a generic framework to aid the ease of adoption of regression-based supervised learning in manufacturing environments. To validate the practicality of the framework, several regression learning techniques are applied to an open-source multi-stage continuous-flow manufacturing process data set to typify inference-driven decision-making that informs the selection of regression learning methods for adoption in real-world manufacturing environments. The investigated regression learning techniques are evaluated in terms of their training time, prediction speed, predictive accuracy (R-squared value), and mean squared error. In terms of training time (TT), k-NN20 (k-Nearest Neighbour with 20 neighbors) ranks first with average and median values of 4.8 ms and 4.9 ms, and 4.2 ms and 4.3 ms, respectively, for the first stage and second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, respectively, over 50 independent runs. In terms of prediction speed (PS), DTR (decision tree regressor) ranks first with average and median values of 5.6784×106 observations per second (ob/s) and 4.8691×106 observations per second (ob/s), and 4.9929×106 observations per second (ob/s) and 5.8806×106 observations per second (ob/s), respectively, for the first stage and second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, respectively, over 50 independent runs. In terms of R-squared value (R2), BR (bagging regressor) ranks first with average and median values of 0.728 and 0.728, respectively, over 50 independent runs, for the first stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, and RFR (random forest regressor) ranks first with average and median values of 0.746 and 0.746, respectively, over 50 independent runs, for the second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process. In terms of mean squared error (MSE), BR (bagging regressor) ranks first with average and median values of 2.7 and 2.7, respectively, over 50 independent runs, for the first stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, and RFR (random forest regressor) ranks first with average and median values of 3.5 and 3.5, respectively, over 50 independent runs, for the second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process. All methods are further ranked inferentially using the statistics of their performance metrics to identify the best method(s) for the first and second stages of the predictive modeling of the multi-stage continuous-flow manufacturing process. A Wilcoxon rank sum test is then used to statistically verify the inference-based rankings. DTR and k-NN20 have been identified as the most suitable regression learning techniques given the multi-stage continuous-flow manufacturing process data used for experimentation.

Modeling and simulation of the furniture manufacturing and assembly process in the arena simulation software

The article describes issues related to creating discrete simulation models for the implementation of the furniture manufacturing and assembly process in a furniture company. The methodology of the manufacturing system analysis was presented, which is aimed to support the appropriate approach to the construction of simulation models. The scope of the work includes the technological identification of the furniture manufacturing and assembly process in real production conditions, on the basis of which the appropriate simulation model was built. The course of the process was analyzed in the Arena software on the basis of a computer simulation based on reports. As a result of the simulation of the manufacturing process with the use of information from report of usage, an area for improvement was located. The re-analysis of the material flow made it possible to propose a change in the input parameters for the simulation model in the indicated area. The results of the second simulation show significant changes in the effective use of workstations and increase in the efficiency of the production line. In practice, it can be the basis for introducing simulated changes in the production system.

Digital twins for electro-physical, chemical, and photonic processes

Manufacturing processes are becoming increasingly data-driven. Integrating manufacturing data and process models in real-time, a digital twin (DT) may function as an autonomous and dynamic digital replica. This, in turn, may enable manufacturers to not only understand and monitor a process but also proactively control it in real-time or a product over its life cycle. This paper examines the DT concept and its evolution and presents a future DT framework. DTs’ key components (e.g., process models) and implementation are focused on additive manufacturing, electrical discharge machining, and electrochemical machining. Furthermore, current challenges and future research directions are summarized.

Active transfer learning for data-driven manufacturing process modelling

Active transfer learning for data-driven manufacturing process modelling

Integration of Industry 5.0 requirements in digital twin-supported manufacturing process selection: a framework

Process selection has been an integral part of manufacturing design and operation, with a close link to manufacturing process modeling. Throughout the years, it has been enriched with many criteria, such as energy efficiency, emissions, resources, and sustainability in general, increasing its complexity in terms of modeling and optimization. Herein, process selection is coupled with (a) the capabilities of the digital twins, (b) the criteria introduced by Industry 5.0 (I5.0) in terms of sustainability and human inclusion, and (c) the opportunities offered by key enabling technologies. A framework is presented capable to implement automated process selection and potentially scheduling through a specific set of integrated technologies, utilizing the concept of the microfactory as a basis in terms of implementation. A case study for the evaluation of two parts, using Additive Manufacturing and laser welding, in different scenarios is presented. It was concluded that the inclusion of the I5.0 criteria not only increases the well-being of the workers but also the energy and time efficiency of the production line, increasing the profit margin.

3D Modeling of the Solidification Structure Evolution and of the Inter Layer/Track Voids Formation in Metallic Alloys Processed by Powder Bed Fusion Additive Manufacturing.

A fully transient discrete-source 3D Additive Manufacturing (AM) process model was coupled with a 3D stochastic solidification structure model to simulate the grain structure evolution quickly and efficiently in metallic alloys processed through Electron Beam Powder Bed Fusion (EBPBF) and Laser Powder Bed Fusion (LPBF) processes. The stochastic model was adapted to rapid solidification conditions of multicomponent alloys processed via multi-layer multi-track AM processes. The capabilities of the coupled model include studying the effects of process parameters (power input, speed, beam shape) and part geometry on solidification conditions and their impact on the resulting solidification structure and on the formation of inter layer/track voids. The multi-scale model assumes that the complex combination of the crystallographic requirements, isomorphism, epitaxy, changing direction of the melt pool motion and thermal gradient direction will produce the observed texture and grain morphology. Thus, grain size, morphology, and crystallographic orientation can be assessed, and the model can assist in achieving better control of the solidification microstructures and to establish trends in the solidification behavior in AM components. The coupled model was previously validated against single-layer laser remelting IN625 experiments performed and analyzed at National Institute of Standards and Technology (NIST) using LPBF systems. In this study, the model was applied to predict the solidification structure and inter layer/track voids formation in IN718 alloys processed by LPBF processes. This 3D modeling approach can also be used to predict the solidification structure of Ti-based alloys processes by EBPBF.

Calibrating uncertain parameters in melt pool simulations of additive manufacturing

Melt pool scale numerical modeling of additive manufacturing (AM) processes can provide predictive capabilities and theoretical insight into the process-property-structure-performance relationships for AM parts. Despite capabilities of numerical models to solve complex multi-physics problems, it is often important to consider a tradeoff between detailed physics and computational cost. Therefore, sources of uncertainty in both experimental conditions and the parameters needed for modeling require models to be validated against empirical evidence. Here, a method is proposed to calibrate uncertain parameters used in continuum-scale melt pool models for powder bed fusion (PBF) AM. Both a simplified heat transfer model and a heat transfer and fluid flow model were investigated. A surrogate model and Markov chain-based optimization algorithm calibrated melt pool geometry for models within experimental variation of the target melt pool width and depth from the NIST AM-Bench 2018-02 dataset. The melt pool temperature distributions, solidification parameters, and simulated multi-layer solidification microstructures were compared between the two models. Similar results from both models indicate that calibrated, lower fidelity numerical models may be used in place of higher fidelity models to generate melt pool solidification data. These calibrated models therefore enable lower computational cost melt pool simulations without a noticeable decrease in simulation accuracy for grain-scale microstructure simulations.

Special Issue on “Modeling, Optimization and Design Method of Metal Manufacturing Processes”

Metal manufacturing processes are essential techniques to convert raw materials into desired metal products, which contributes significantly to the growth of industry and our society [...]

Editorial: Advances in computational modeling of additive manufacturing processes

Editorial: Advances in computational modeling of additive manufacturing processes

Reduced order dynamical models for complex dynamics in manufacturing and natural systems using machine learning

Dynamical analysis of manufacturing and natural systems provides critical information about production of manufactured and natural resources, respectively. Current dynamic models for full industrial process plants exist as highly accurate first-principle relationships. However, their integration is computationally intensive and provides no simplified understanding of the underlying mechanisms driving the overall dynamics. Similarly, for natural systems, most dynamical models are first principle based, with high data requirements and low state accuracy. Consequently, lower-order models that may sacrifice accuracy for simplicity and ease of training can prove useful. Yet, there have been few attempts at finding low-order models of chemical manufacturing processes and natural systems, with work focusing on modeling individual mechanisms. We seek to fill this research gap by using a machine learning (ML) approach, SINDy, validated on a soybean-diesel process plant and watershed system. This ML method combines sparse, grey-box modeling with additional nonlinear optimization to identify governing dynamics as ODEs. We find a linear ODE model for the process plant that gives an accurate relation between input and output and selected internal molar flow rates reflective of underlying linear stoichiometric mechanisms and an internal mass balance. For the natural system, we modify the SINDy approach to include the effect of past dynamics on training the model, which gives a nonlinear model for streamflow dynamics. This improves dynamical transitions, but falls short of accurate state estimation. We conclude that the proposed ML approach works well for non-chaotic systems with minimal hysteresis, but is limited when this condition is not met.

Towards Multi-Scale Modeling of Zirconium Alloys Recrystallization and Application to Thermo-Mechanical Processes Optimization

Zirconium alloys are used in the nuclear industry due to their low neutron capture cross-section and resistance to corrosion, irradiation and creep. The microstructure of the nuclear fuel components evolves during the manufacturing route and can impact the subsequent processes or the final properties. Thus, numerical modeling of thermo-mechanical manufacturing processes is of interest to understand and master these microstructure evolutions.Numerical modeling of thermo-mechanical manufacturing processes with FORGE® NxT software is applied. These models provide the thermo-mechanical history of the material at each integration point of the finite element (FE) mesh, which can be used to assess locally the continuous dynamic and post-dynamic recrystallization during hot extrusion.Mean-field models were developed in Python and integrated into FORGE® NxT software, to quantify the microstructure evolution at the macro-scale of the component. Full-field models (DIGIMU® software1) were also developed for considering microstructural heterogeneities and the influence of initial microstructure at the mesoscopic scale while improving the mean-field equations by homogenization.After validation based on experimental results, these two recrystallization models provide complementary information to optimize the process parameters at the macro-scale and to better understand mesoscopic scale phenomena, such as:• At the macro-scale: influence of hot extrusion parameters on the continuous dynamic and post-dynamic recrystallization of Zircaloy-4.• At the meso-scale: influence of the initial microstructure on the recrystallization phenomena with improved precision. Indeed, the topology of the microstructure is predicted and not only the mean values/distributions of the state variables.

Concept of High-Tech Enterprise Development Management in the Context of Digital Transformation

The purpose of this article is to check and identify management gaps that lead to the formation of digitalization problems in enterprises in the context of Industry 4.0 and to offer a conceptual approach to managing the development of high-tech enterprises in digital transformation. The paper substantiates the concept of digital transformation management in a high-tech enterprise based on interdependent adaptive systems for planning digital transformation processes, monitoring, and change management. The paper considers the idea of the Industry 4.0 concept and presents principal technologies and tools that contribute to the gradual transition to digital transformation. It is determined that digital transformation is a process of transition to digital business, which involves the use of digital technologies to change business processes in the company and provision of new opportunities for additional income and development prospects. A conceptual model of enterprise competitiveness formation in the process of digital transformation has been developed, which includes organizational and economical digital tools for sustainable development of high-tech enterprises and synergies from the organization of new forms of digital interaction. The proposed methodology for managing the development of high-tech enterprises in the context of digital transformation is based on the formation of an ecosystem model of decentralization in a single distributed digital space, based on interconnected adaptive systems of planning, monitoring, and change management, and, on the basis of modeling and forecasting of complex manufacturing and logistics processes of high-tech industries, it allows effective implementation of the innovative order portfolio in the short term and with limited opportunities while coordinating the priorities of the business strategy and strategy of digital transformation of high-tech enterprises.

INN: An Interpretable Neural Network for AI Incubation in Manufacturing

Both artificial intelligence (AI) and domain knowledge from human experts play an important role in manufacturing decision making. Smart manufacturing emphasizes a fully automated data-driven decision-making; however, the AI incubation process involves human experts to enhance AI systems by integrating domain knowledge for modeling, data collection and annotation, and feature extraction. Such an AI incubation process not only enhances the domain knowledge discovery but also improves the interpretability and trustworthiness of AI methods. In this article, we focus on the knowledge transfer from human experts to a supervised learning problem by learning domain knowledge as interpretable features and rules, which can be used to construct rule-based systems to support manufacturing decision making, such as process modeling and quality inspection. Although many advanced statistical and machine learning methods have shown promising modeling accuracy and efficiency, rule-based systems are still highly preferred and widely adopted due to their interpretability for human experts to comprehend. However, most of the existing rule-based systems are constructed based on deterministic human-crafted rules, whose parameters, such as thresholds of decision rules, are suboptimal. Yet the machine learning methods, such as tree models or neural networks, can learn a decision rule based structure without much interpretation or agreement with domain knowledge. Therefore, the traditional machine learning models and human experts’ domain knowledge cannot be directly improved by learning from data. In this research, we propose an interpretable neural network (INN) model with a center-adjustable sigmoid activation function to efficiently optimize the rule-based systems. Using the rule-based system from domain knowledge to regulate the INN architecture not only improves the prediction accuracy with optimized parameters but also ensures the interpretability by adopting the interpretable rule-based systems from domain knowledge. The proposed INN will be effective for supervised learning problems when rule-based systems are available. The merits of the INN model are demonstrated via a simulation study and a real case study in the quality modeling of a semiconductor manufacturing process. The source code of this work is hosted here: https://github.com/XiaoyuChenUofL/Interpretable-Neural-Network .

Self-Attention-Augmented Generative Adversarial Networks for Data-Driven Modeling of Nanoscale Coating Manufacturing.

Nanoscale coating manufacturing (NCM) process modeling is an important way to monitor and modulate coating quality. The multivariable prediction of coated film and the data augmentation of the NCM process are two common issues in smart factories. However, there has not been an artificial intelligence model to solve these two problems simultaneously. Focusing on the two problems, a novel auxiliary regression using a self-attention-augmented generative adversarial network (AR-SAGAN) is proposed in this paper. This model deals with the problem of NCM process modeling with three steps. First, the AR-SAGAN structure was established and composed of a generator, feature extractor, discriminator, and regressor. Second, the nanoscale coating quality was estimated by putting online control parameters into the feature extractor and regressor. Third, the control parameters in the recipes were generated using preset parameters and target quality. Finally, the proposed method was verified by the experiments of a solar cell antireflection coating dataset, the results of which showed that our method performs excellently for both multivariable quality prediction and data augmentation. The mean squared error of the predicted thickness was about 1.6~2.1 nm, which is lower than other traditional methods.

Reusing and Extending Standards-Based Unit Manufacturing Process Models for Characterizing Sustainability Performance

Abstract Over the past two decades, numerous efforts have characterized manufacturing processes for sustainability performance. These efforts have been pursued primarily by manufacturing researchers in academic and governmental labs, and involve the development of frameworks, methodologies, and standards for characterizing discrete manufacturing processes and their representation as information models. Furthermore, characterization of sustainability performance of manufacturing process flows has been attempted through linking, or composing, these unit manufacturing process (UMP) models. This paper reviews these efforts and identifies existing research gaps that should be addressed by academic, industrial, and governmental researchers. The review includes the relevant sustainable manufacturing standards that have been recently published by ASTM International. A methodology for creating and extending composable models of UMPs that build upon these standards is presented. This research demonstrates how formalization of these prior efforts can address the identified gaps. It is shown that the reuse of UMP models can be enabled by encapsulating specific characteristics of complex processes into information models that can be applied for detailed process analysis and evaluation. This research proposes the concept of a template UMP information model, which can further be abstracted and customized to represent an application-specific, higher-order manufacturing process model. The template model concept is illustrated for manual and computer numerically controlled (CNC) milling processes.