Automotive Manufacturing Research Articles

Synthetic X-ray Image Generation for Non-Destructive Testing using Generative Adversarial Networks

Developing and optimizing a Machine Learning (ML) based Non-Destructive Testing (NDT) tool for automotive manufacturing can be challenging due to the need for a significant amount of annotated training data. Obtaining such an extent of real X-ray images of different defects can be challenging and expensive. Hence, generating synthetic images with adequate defects is a viable option to fill this gap. This contribution presents a novel approach that harnesses Generative Adversarial Networks (GANs) to simulate industrial X-ray images of specific parts of a car wheel (rim and spokes) with defects and their annotations. The presented method draws inspiration from techniques used in medical healthcare radiography as well as the NDT field for simulating synthetic X-ray images. We propose a novel deep neural network architecture for generating high-resolution X-ray images of size 1024 x 512 pixels with porous defects in specified locations. These images are automatically generated from edge masks of the desired structure. We conducted separate evaluations for both, the generated images and the included defects. To assess the generated image quality, we used image properties and structural similarity metrics. The generated images achieved an MSSIM index of over 0.90. We analyzed the local gray-scale profile of synthetic images to evaluate the quality of generated defects. A state-of-the-art defect detector (ISAR, developed by Fraunhofer EZRT) was used to estimate defect detection based on various IoU thresholds. In conclusion, the presented research demonstrates the feasibility of leveraging GANs to generate synthetic 2D X- ray image data, including defects for training ML-based NDT tools. This approach opens new possibilities for developing and optimizing robust NDT solutions by overcoming the challenges of obtaining real data with defects.

Effect on wetting properties of the Al-Ti system by the addition of different alloying elements

With lightweight and high-strength, Al-Ti composites have become one of the indispensable materials in the aerospace and automotive manufacturing fields. However, due to strong interfacial reactions, the traditional pure Al-Ti composites have been limited in practical applications. To better control the interfacial reaction between the reinforced phase and the matrix in the Al-Ti composites, in this paper, the effect on wetting behavior and interfacial properties of the Al-Ti system by the addition of different alloying elements (Si, Mg, Zn, Cu) in Al melt were systematically investigated using the sessile drop method. According to the results, adding Si, Mg, Zn, and Cu elements to the Al melt can increase the steady-state wetting angle to varying degrees at the end of the holding period compared to the pure Al-Ti wetting but still maintains good wettability. The Mg, Zn, and Cu elements ensure good wettability and simultaneously reduce the temperature required for wetting, providing novel ideas for preparing aluminum matrix composites. All the systems in this experiment are typical of reactive wetting. The system with added Si and Cu showed a clear interfacial layer at the Al-Ti interface, which was comparatively smooth, and both the original Al-Ti reaction at the interface and the dissolution of the Ti substrate are inhibited.

A method to assist designers in optimizing the exterior styling of vehicles based on key features

Aiming to assist the design and management personnel of automotive products to make correct judgments and give optimization solutions for the design of exterior styling, and to solve the defects of the traditional method which relies too much on experience and personal ability, a neural network-based key feature analysis and optimization method of styling is proposed. Firstly, the user attributes are analyzed and quantified, and the weighted optimization of user evaluation data is completed based on the multidimensional Gaussian distribution function to construct a more objective car styling evaluation dataset. Secondly, a particle swarm algorithm is proposed to optimize the prediction model of radial basis function neural network (PSO-RBFNN) which deeply analyzes the mapping relationship between different car perspectives and users’ perceptual preferences. The identification of styling components is completed with the annotation of feature points, and a parametric expression method of styling feature data with multi-viewpoint weight optimization is proposed. Third, the model interpretation is based on the embedded feature selection method to discover the key feature points affecting user perception, and the key common features of styling are obtained through the coupling relationship analysis of feature points. Finally, the optimal distribution range of key features is given based on statistical analysis, and the application process is shown by an example of optimization to verify the feasibility of the theory. Compared with the traditional methods, PSO-RBFNN has better prediction accuracy. Meanwhile, the modeling optimization method based on key features has the great advantages of objective accuracy and high efficiency compared with the traditional theory.

Adaptation of the Automotive Product Development Process for AI Development

Abstract Artificial Intelligence (AI) functionalities are increasingly being used in vehicle applications. While current product development models take the increasing proportion of software into account, the special requirements of artificial intelligence developments are hardly ever explicitly considered. The new requirements result both from increasing standardisation and regulation and from the iterative and explorative approach inherent in AI model development. This paper identifies the key adaptations to the standard automotive product development process that are required to cover the requirements of AI development. The adapted development model was trialled in two vehicle developments, the most important lessons learnt of which are summarised in this paper.

Smart platforming in automotive manufacturing for NetZero: Intelligentization, green technology, and innovation dynamics

Green technology innovation is integral to fostering sustainable economic development and environmental conservation. The application of smart product platform has emerged as a transformative force in shaping the trajectory of green technology innovation. Drawing on the foundation of knowledge theory and utilizing a sample of 1240 valid cases from listed Chinese automotive manufacturing enterprises between 2013 and 2022, this paper employs a mixed regression method to explore the relationship between smart product platform usage and green technology innovation. Additionally, it analyzes the mediating role of corporate innovation input in this relationship and the moderating effect of intelligentization level on the association between smart product platform usage and green technology innovation. The research reveals the following key findings: (1) Corporate smart product platform usage and innovation input significantly and positively drive green technology innovation. (2) Innovation input acts as a complete mediator in the relationship between smart product platform usage and green technology innovation. (3) Corporate intelligentization level positively moderates the relationship between smart product platform usage and innovation input. (4) Considering regional and ownership attribute disparities, the impact of smart product platform usage on green technology innovation is asymmetric. This study, as one of the few empirical examinations of the effects of smart product platform, enriches research in the areas of smart product platform and green technology innovation. The study, contributing to the empirical understanding of smart product platforms, offers valuable insights for automotive manufacturing enterprises to strategically leverage these platforms for advanced and flexible operations, aligning with the imperative of achieving global environmental goals such as NetZero. As indicated in COP28, the findings underscore the urgency of integrating smart technologies into the automotive industry to advance these crucial environmental objectives.

Negative Poisson's Ratio Material Structure Based on 3D Printing and Its Application in Medical Field

First of all, the overall framework of 3D printing is briefly introduced, including the basic principles of the additive manufacturing process, the classification and summary of the seven processes. Secondly, the common negative Poisson's ratio structure is introduced. Compared with the conventional structure, the negative Poisson's ratio structure has stronger energy absorption capacity, better fracture resistance and better indentation resistance, which are its advantages in printing manufacturing. Finally, 3D printing, the application of negative Poisson's ratio structure and the combination of the two are introduced from the different perspective of medical field, for example, the application of cardiovascular stent, biomedical material structure preparation, and lumbar disc implants. This paper suggests that the structural design of negative Poisson's ratio in 3D printing guides the development of new application directions in the medical field. Negative Poisson's ratio materials have a wide range of applications, not only in the medical field but also in mechanical equipment, automotive manufacturing, aerospace, and other high-tech industries.

The Effect of Using Environmentally Friendly Materials and Energy Efficiency in the Production Process on Reducing Carbon Emissions in the West Java Automotive Industry

This research quantitatively analyzes the effect of integrating environmentally friendly materials and energy-efficient production processes on reducing carbon emissions in the West Java automotive industry. Through surveys and statistical analysis, the study examines the adoption of sustainable practices among automotive manufacturers and assesses their impact on carbon emissions reduction. Findings indicate that companies actively embracing sustainable practices demonstrate a significant reduction in carbon emissions compared to those with minimal adoption. The results underscore the importance of prioritizing sustainability initiatives within the automotive industry to mitigate environmental impacts and contribute to global efforts to combat climate change.

Three-dimensional super-resolution crack imaging in industrial manufactured components: A truncated correlation photothermal coherence tomography approach

The challenge of detecting cracks in powder metallurgy (PM) components has been a topic of interest for many years, with no practical commercial solution currently in place. This study employs enhanced truncation-correlation photothermal coherence tomography (eTC-PCT) to visualize 3D cracks within PM automotive parts. Through the application of effective diffusion-wave reversal techniques, blurred infrared thermophotonic images of subsurface defects (cracks) in (“green”) compressed metal PM components were restored to their original geometric resolution over the entire depth range. This approach enabled the creation of 3-dimensional depth-resolved photothermal tomographic images and cross-sectional mappings of cracks. The developed technique reveals the precise spatial dimensions of surface and subsurface cracks, reaching depths of down to 3 mm (not an upper limit) that conventional thermal imaging cannot access due to limitations imposed by the depth-integrated nature of conventional thermal-wave imaging, the properties of PM materials, and the physics of spreading diffusion. The super-resolution method was further applied to a sintered automotive part, specifically validating the efficacy of eTC-PCT for non-destructive imaging (NDI) in manufactured automotive components. Diffusion reversal imaging shows promise as a non-destructive testing (NDT) tool, with potential applications in a wide range of manufactured products, including both the green and sintered stages of automotive component production.

Integrated operations planning model for the automotive wiring industry

An integrated operations planning model for automotive wiring companies is studied to improve synchronization between production activities and inventory flows. These combined factors are growing in significance as they drive the need to take proactive steps in manufacturing and distributing wiring materials within the supply chain. This involves anticipating the requirements of different automotive manufacturers and thereby guaranteeing a consistent, uninterrupted, and punctual provision of raw wiring materials. This support is vital for sustaining the ongoing manufacturing operations in the automotive sector. For this push flow system, the proposed operational model is based on integer linear programming, considering capacity and bill of materials constraints to determine production quantities, inventory levels, and machine sizing. Real-life data from the automotive wiring industry validates the effectiveness of coordinated production and inventory activities, resulting in significant lead time reductions of up to 60 %. These findings provide compelling reasons for automotive wiring partners to engage in joint operations planning.

An interactive framework to support decision-making for Digital Twin design

Producing a Digital Twin (DT) involves many inter-linking decisions. Existing research tends to describe the parts of a DT and how they work, but not the decision-making that goes into building a DT nor the consideration of alternative design options. There is therefore a need for decision support to guide developers to create DTs efficiently while meeting functional requirements such as accuracy and interoperability. This paper presents an ontology-based decision support framework to achieve this need. Firstly an analysis of the decisions required to create a predictive maintenance DT for an automotive manufacturer is performed. The analysis found that each decision point produces an output by consideration of various influencing factors, such as time constraints, computation limits and the required fidelity of the model. The network of decisions is complex, with the outcomes of earlier decisions influencing later ones. An IDEF0 diagram was found to be a useful way to represent decisions, their dependencies and their cross-linking. This knowledge was used to populate an ontology of DT components for a predictive maintenance DT. The ability of an ontology to describe concepts explicitly using standardised vocabulary ensures the integrity of the decision-making guidance. A demonstration of the functionality of the ontology-based decision support framework was made before an evaluation of the concept. The research is a fundamental component in producing decision support for DT creators so that manufacturers can realise the benefits of a connected, responsive and flexible facility.

Evaluation of Industry 4.0 strategies for digital transformation in the automotive manufacturing industry using an integrated fuzzy decision-making model

The current paper proposes a methodological frame to identify the best Industry 4.0 (I4) strategy for the automotive manufacturing industry as a roadmap for companies to make a more straightforward digital transformation. We noticed a critical research gap when we performed an extensive literature review. Although there are many studies available that assess the readiness of companies for I4, only a few deal with decision-making in terms of sustainable development, and none have applied that to the automotive industry. Practitioners can apply the proposed model to determine the strategy based on technological developments in I4. The current paper proposes an extended version of the combined compromise solution approach with the help of the picture fuzzy sets. According to the paper's results, by using the proposed model, developing a new business model based on technological improvements is the best strategy for the digital transformation of the automotive industry. Also, the lack of research and development implementations on I4 implementation is the most influential factor. Hence, practitioners in the automotive industry know the significance of research and development in reaching successful results for digital transformation. The acquired outcomes of the paper show that developing technology-based new business models is the best strategy for the automotive manufacturing industry concerning digital transformation instead of accommodating traditional business models and high technology utilization.

Optimizing scope 3 emissions in the automotive manufacturing industry: a multidisciplinary approach

The acceleration of global climate change poses enormous challenges to the automotive manufacturing industry, a key sector in reducing greenhouse gas (GHG) emissions. Particularly, Scope 3 emissions, encompassing indirect emissions, often constitute the largest carbon footprint component in this sector, yet their quantification and management remain challenging. This paper proposes an interdisciplinary approach that integrates cloud computing, text analysis, and machine learning, and systematically details its implementation, key benefits, and potential applications. Through this methodology, the paper seeks to provide the automotive industry with innovative and actionable insights to tackle the complexities of Scope 3 emissions. It focuses on enhancing the accuracy of emission quantification and optimizing supply chains, aiming to reduce the overall carbon footprint. Moreover, this paper outlines the future challenges and directions for these technologies and methodologies in sustainable development and environmental management. This work underlines the critical role of interdisciplinary approaches in resolving environmental challenges, setting the stage for the automotive industry to forge paths towards a greener future.Graphical

Reducing Tyre Wear Emissions of Automated Articulated Vehicles through Trajectory Planning.

Effective emission control technologies and eco-friendly propulsion systems have been developed to decrease exhaust particle emissions. However, more work must be conducted on non-exhaust traffic-related sources such as tyre wear. The advent of automated vehicles (AVs) enables researchers and automotive manufacturers to consider ways to further decrease tyre wear, as vehicles will be controlled by the system rather than by the driver. In this direction, this work presents the formulation of an optimal control problem for the trajectory optimisation of automated articulated vehicles for tyre wear minimisation. The optimum velocity profile is sought for a predefined road path from a specific starting point to a final one to minimise tyre wear in fixed time cases. Specific boundaries and constraints are applied to the problem to ensure the vehicle's stability and the feasibility of the solution. According to the results, a small increase in the journey time leads to a significant decrease in the mass loss due to tyre wear. The employment of articulated vehicles with low powertrain capabilities leads to greater tyre wear, while excessive increases in powertrain capabilities are not required. The conclusions pave the way for AV researchers and manufacturers to consider tyre wear in their control modules and come closer to the zero-emission goal.

Stock market reaction to new energy vehicle industry development plan: an event study in China

ABSTRACT The targets of energy conservation, decarbonization, and industry reinvigoration have significantly influenced the design of China’s new energy vehicle (NEV) industrial policies and nationwide electrification. As a monumental policy framework for energy transition in transportation sector, the NEV industry development plan plays an influential role in promoting cleantech diffusion and enhancing NEV competitiveness. This study employs an event study method to investigate the stock market reaction to the NEV plan shocks. The NEV plan announced in 2020 receives a markedly positive stock price effect of 3.72% in the 6-day event window. Heterogeneity tests on subsamples indicate that state-backed entities exhibit a similar effect to the total sample, while the automotive manufacturing class and original equipment manufacturers see a significantly higher market value gain of 6.56% and 13.34%, respectively. However, battery manufacturers, as one of the key participants in the NEV value chain, experience an insignificant stock price effect. This study documents the financial consequences of clean energy policies specific to the emission-intensive automotive manufacturing sector, highlights the effectiveness of government-to-investor signalling in a cleantech diffusion context, and reveals the implications to other economies seeking to deploy clean transport and enhance environmental sustainability.

Germany's Economic Integration: Automotive Industry and FDI Analysis

In this paper, Germany's significant role was explored in regional integration and its competitive edge in the automotive manufacturing industry, underlining the country's strategic involvement in the European Union and World Trade Organisation. Germany’s participation in the EU has been instrumental in promoting economic integration across Europe, benefiting from free trade agreements and contributing to the EU’s status as a major trade bloc. The paper also delves into the reasons behind Germany's prowess in the automotive sector, using Porter's Diamond Model to analyze factors like advanced technology, skilled workforce, strict consumer standards, and supportive industries, all contributing to the country's global competitiveness in this domain. Furthermore, the study investigates the dynamics of Foreign Direct Investment (FDI) in Germany, identifying key attractions for foreign investors such as technological leadership, a robust market, efficient infrastructure, and favorable investment policies. However, challenges like rigorous government regulations on FDI and cultural differences pose potential hurdles for foreign investors. The conclusion emphasizes that while Germany offers substantial opportunities due to its economic strength and market potential, foreign entities must carefully navigate these challenges to successfully invest and operate in the German market.

Lean Six Sigma and Industry 4.0 implementation framework for operational excellence: a case study

The adoption of Lean Six Sigma (LSS) 4.0 has been recommended by researchers and practitioners as an effective strategy to enhance the operational excellence of companies, especially in highly competitive environments given the complementarity of LSS with Industry 4.0 (I4.0). Moreover, evidence suggests that companies commonly face difficulties and perceive the implementation process as challenging. To the best of our knowledge, there is currently no comprehensive global model available that offers a step-by-step approach for implementing LSS4.0. The purpose of this study is, therefore, to develop a structured framework that directs organizations to successfully implement LSS4.0. This study follows a combined approach including a systematic literature review to identify existing gaps in recent research and an expert panel to provide valuable insights and validation during the development of the framework. Additionally, a case study was conducted in an automotive manufacturing company to validate the findings. The proposed LSS4.0 framework is based on the DMAIC approach subdivided into fifteen steps. It permits managers to seamlessly integrate LSS4.0 into their processes and selectively choose the relevant tools as required, avoiding digitalization without a clear purpose. Also, it offers a comprehensive solution for managers addressing contemporary industry challenges and enhancing operational processes.

Semi-supervised method for visual detection of automotive paint defects

Automotive paint defect detection plays a crucial role in the automotive production process. Current research on visual defect detection methods is mainly based on supervised learning, which requires a large number of labeled image samples for model training. The labeling work is not only time consuming but also expensive, seriously hindering the testing and application of these models in practice. To address this issue, this study proposes a new method for automotive paint defect detection based on a semi-supervised training strategy. First, a semi-supervised automotive paint defect detection framework, which can use labeled and unlabeled samples to reduce the cost of data labeling effectively, is presented. Then, a spatial pyramid pooling fast external attention module that introduces an external attention mechanism is proposed to improve the traditional YOLOv7 network structure, called YOLOv7-EA, to obtain good detection performance. This network acts as a detector to generate high-quality pseudo labels for the unlabeled samples, providing additional data to train the model; meanwhile, it performs the final detection task. Lastly, a Wise-intersection over union loss function that considers the quality of the anchor box is introduced to reduce the interference of low-quality samples and improve the convergence speed and detection accuracy of the model. Using this method, we can accomplish the task of automotive paint defect detection with a small number of labeled image samples. Experimental results on the automotive paint defect dataset show that mean average precision (mAp)@.5, mAp@.75, and mAp@.5:.95 are superior to other methods under the condition of 10% and 15% labeled data, achieving good defect detection performance.

The Effects of B on the Microstructure and Corrosion Resistance of Zn–6Al–3Mg Alloy Coating

Hot dip galvanized zinc‐aluminum‐magnesium steel plates are widely used in fields such as power communication, automotive manufacturing, and marine engineering due to their excellent corrosion resistance. The use of microalloying can further improve their corrosion resistance. The effects of B on the microstructure and corrosion resistance of Zn–6Al–3Mg (ZAM) alloy coatings are systematically examined. Data indicates that the eutectic structure of the coating progressively refines as B content increases, concomitant with a reduction in the thickness of the Fe2Al5 inhibition layer owing to the augmented formation of an Al‐rich phase at the surface. When the addition of B reaches 0.12%, the microstructure of the alloy coating is minimized, and there is no further reduction in the thickness of the Fe2Al5 inhibition layer. Moreover, the presence of B diminishes the corrosion current density and bolsters corrosion resistance. Optimal corrosion performance, indicated by maximal density and uniformity of surface corrosion products and the lowest corrosion current density, is achieved at a B addition of 0.12%. The judicious selection of B content is pivotal for enhancing the microstructural and anti‐corrosive properties of ZAM alloy coatings. Therefore, adding 0.12% B to ZAM alloy can effectively improve the microstructure and corrosion resistance of the alloy coating.

Abrasive waterjet cutting of r‐GO infused magnesium fiber metal laminates: Experimental investigations and optimization through gorilla troops algorithm

AbstractLaminated metal‐composite structures, known as fiber metal laminates (FMLs), are modern lightweight materials extensively utilized in diverse industries such as aerospace and automotive manufacturing. These materials offer enhanced impact and fatigue resistance, making them invaluable for various applications. However, machining FMLs poses a challenge due to the occurrence of delamination and heterogenous in nature during conventional methods. Therefore, this study aims to investigate the quality characteristics such as kerf width, surface roughness and kerf taper of Magnesium based FMLs processed with an unconventional machining process namely abrasive water jet cutting (AWJC). These FMLs comprise alternately stacked kevlar/carbon fibers adhesively bonded with epoxy resin matrix filled with varying wt% of reduced graphene oxide (r‐GO), combined with AZ31B alloy sheet as the skin material. AWJC experiments were performed by varying the process parameters including waterjet pressure (275–325 MPa), stand‐off distance (2.5–3.5 mm), and cutting speed (600–800 mm/min) based on the box–behnken experimental design. The findings from the statistical analysis underscore the significant influences of stand‐off distance and waterjet pressure on kerf characteristics, while the inclusion of r‐GO is observed to notably affect the surface quality. In pursuit of enhancing cut quality, a multi‐response optimization was conducted employing the Gorilla Troops Optimization (GTO) algorithm. Comparative analysis with established metaheuristics like the gray wolf algorithm, dragonfly algorithm, and harmony search algorithm reveals GTO's superior performance across various metrics, including rapid convergence, diversity, and spacing values. Further, the cutting‐induced damages such as matrix plowing, fiber‐metal debonding and composite delamination were observed through microstructure analysis.Highlights Magnesium (AZ31B) fiber metal laminate comprising with various wt% of reduced graphene oxide was fabricated. Abrasive waterjet cutting of FMLs were performed based on box–behnken design experimental approach. Statistical analysis and influence of process parameters on the kerf width, surface roughness and kerf taper were investigated. Multi‐response optimization was carried out using metaheuristic‐based gorilla troops algorithm.

Transforming Operations: A Comprehensive Analysis of Industry 4.0 Technologies in Operations Management

In the introductory part of this paper, we provide a brief overview of the research subject matter, research topic, research problem, thesis topic, research questions, and disposition of this paper. Background Industry 4.0 brings about a major transformation in automotive manufacturing. It is characterized by the use of advanced information analytics, networked machines, and digitalization within organizations. In addition, it is characterized by the integration of internet technologies with forward-looking technologies in the domain of "smart" objects. However, there is no single definition of the term "industry 4.0" in the literature, which restricts theory building and the comparability of research. However, Lasi (2014) argues that industry 4-0 is a "new paradigm shift" in industrial production because of the advanced digitalisation within factories. A paradigm shift is a significant change that occurs when the normal way of thinking or doing something changes to something new and different. In industry 4-0, emerging technologies integrate with each other to bring about a change in manufacturing processes.