Sofiene Lassoued, Laxmikant Shrikant Bahetic, Nathalie Weiß-Borkowskib
et al.
Flexible Manufacturing Systems (FMS) are pivotal in optimizing production processes in today's rapidly evolving manufacturing landscape. This paper advances the traditional job shop scheduling problem by incorporating additional complexities through the simultaneous integration of automated guided vehicles (AGVs) and tool-sharing systems. We propose a novel approach that combines Colored-Timed Petri Nets (CTPNs) with actor-critic model-based reinforcement learning (MBRL), effectively addressing the multifaceted challenges associated with FMS. CTPNs provide a formal modeling structure and dynamic action masking, significantly reducing the action search space, while MBRL ensures adaptability to changing environments through the learned policy. Leveraging the advantages of MBRL, we incorporate a lookahead strategy for optimal positioning of AGVs, improving operational efficiency. Our approach was evaluated on small-sized public benchmarks and a newly developed large-scale benchmark inspired by the Taillard benchmark. The results show that our approach matches traditional methods on smaller instances and outperforms them on larger ones in terms of makespan while achieving a tenfold reduction in computation time. To ensure reproducibility, we propose a gym-compatible environment and an instance generator. Additionally, an ablation study evaluates the contribution of each framework component to its overall performance.
In manufacturing systems, identifying the causes of failures is crucial for maintaining and improving production efficiency. In knowledge-based failure-cause inference, it is important that the knowledge base (1) explicitly structures knowledge about the target system and about failures, and (2) contains sufficiently long causal chains of failures. In this study, we constructed Diagnostic Knowledge Ontology and proposed a Function-Behavior-Structure (FBS) model-based maintenance-record accumulation method based on it. Failure-cause inference using the maintenance records accumulated by the proposed method showed better agreement with the set of candidate causes enumerated by experts, especially in difficult cases where the number of related cases is small and the vocabulary used differs. In the future, it will be necessary to develop inference methods tailored to these maintenance records, build a user interface, and carry out validation on larger and more diverse systems. Additionally, this approach leverages the understanding and knowledge of the target in the design phase to support knowledge accumulation and problem solving during the maintenance phase, and it is expected to become a foundation for knowledge sharing across the entire engineering chain in the future.
The applied research is the design and development of an automated folding and sewing machine for pleated pants. It represents a significant advancement in addressing the challenges associated with manual sewing processes. Traditional methods for creating pleats are labour-intensive, prone to inconsistencies, and require high levels of skill, making automation a critical need in the apparel industry. This research explores the technical feasibility and operational benefits of integrating advanced technologies into garment production, focusing on the creation of an automated machine capable of precise folding and sewing operations and eliminating the marking operation. The proposed machine incorporates key features such as a precision folding mechanism integrated into the automated sewing unit with real-time monitoring capabilities. The results demonstrate remarkable improvements: the standard labour time has been reduced by 93%, dropping from 117 seconds per piece to just 8 seconds with the automated system. Similarly, machinery time improved by 73%, and the total output rate increased by 72%. These enhancements translate into a cycle time reduction from 117 seconds per piece to an impressive 33 seconds, enabling manufacturers to meet customer demand more swiftly. By eliminating manual marking processes, the machine not only reduces labour costs but also minimizes waste through consistent pleat formation. This automation aligns with industry trends toward sustainability and efficiency, potentially reducing environmental impact by decreasing material waste and energy consumption.
Scheduling is a key decision-making process to improve the performance of flexible manufacturing systems. Place-timed Petri nets provide a formal method for graphically modeling and analyzing such systems. By generating reachability graphs and combining intelligent search algorithms, operation sequences from the initial state to the target state can be found for the underlying system. However, the reachability graph grows exponentially with the system size increases, which is the main challenge of existing methods for scheduling large systems. To this end, we develop an efficient improved beam search algorithm to optimize the makespan based on a compact representation of reachability graph called basis reachability graph. The key idea behind the proposed method is to form a state together with the basis markings and its corresponding transition sequences, and evaluate the cost of the state based on the resource idle time. Experimental results are conducted on several benchmark systems which show that the developed method improves the search efficiency while ensuring the quality of the solution compared with existing methods.
Rising electricity demand underscores the need for secure and reliable generation expansion planning that accounts for upstream supply chain constraints. Traditional models often overlook limitations in materials, manufacturing capacity, lead times for deployment, and field availability, which can delay availability of planned resources and thus to threaten system reliability. This paper introduces a multi-stage supply chain-constrained generation expansion planning (SC-GEP) model that optimizes long-term investments while capturing material availability, production limits, spatial and temporal constraints, and material reuse from retired assets. A decomposition algorithm efficiently solves the resulting MILP. A Maryland case study shows that supply chain constraints shift technology choices, amplify deployment delays caused by lead times, and prompt earlier investment in shorter lead-time, low-material-intensity options. In the low-demand scenario, supply chain constraints raise investment costs by $1.2 billion. Under high demand, persistent generation and reserve shortfalls emerge, underscoring the need to integrate upstream constraints into long-term planning.
This paper focuses on the generalized grouping problem in the context of cellular manufacturing systems (CMS), where parts may have more than one process route. A process route lists the machines corresponding to each part of the operation. Inspired by the extensive and widespread use of network flow algorithms, this research formulates the process route family formation for generalized grouping as a unit capacity minimum cost network flow model. The objective is to minimize dissimilarity (based on the machines required) among the process routes within a family. The proposed model optimally solves the process route family formation problem without pre-specifying the number of part families to be formed. The process route of family formation is the first stage in a hierarchical procedure. For the second stage (machine cell formation), two procedures, a quadratic assignment programming (QAP) formulation, and a heuristic procedure, are proposed. The QAP simultaneously assigns process route families and machines to a pre-specified number of cells in such a way that total machine utilization is maximized. The heuristic procedure for machine cell formation is hierarchical in nature. Computational results for some test problems show that the QAP and the heuristic procedure yield the same results.
The current landscape of massive production industries is undergoing significant transformations driven by emerging customer trends and new smart manufacturing technologies. One such change is the imperative to implement mass customization, wherein products are tailored to individual customer specifications while still ensuring cost efficiency through large-scale production processes. These shifts can profoundly impact various facets of the industry. This study focuses on the necessary adaptations in shop-floor production planning. Specifically, it proposes the use of efficient evolutionary algorithms to tackle the flowshop with missing operations, considering different optimization objectives: makespan, weighted total tardiness, and total completion time. An extensive computational experimentation is conducted across a range of realistic instances, encompassing varying numbers of jobs, operations, and probabilities of missing operations. The findings demonstrate the competitiveness of the proposed approach and enable the identification of the most suitable evolutionary algorithms for addressing this problem. Additionally, the impact of the probability of missing operations on optimization objectives is discussed.
Chi Chung Li, Joseph Toombs, Vivek Subramanian
et al.
The capability of holography to project three-dimensional (3D) images and correct for aberrations offers much potential to enhance optical control in light-based 3D printing. Notably, multi-beam multi-wavelength holographic systems represent an important development direction for advanced volumetric additive manufacturing (VAM). Nonetheless, searching for the optimal 3D holographic projection is a challenging ill-posed problem due to the physical constraints involved. This work introduces an optimization framework to search for the optimal set of projection parameters, namely phase modulation values and amplitudes, for multi-beam holographic lithography. The proposed framework is more general than classical phase retrieval algorithms in the sense that it can simultaneously optimize multiple holographic beams and model the coupled non-linear material response created by co-illumination of the holograms. The framework incorporates efficient methods to evaluate holographic light fields, resample quantities across coordinate grids, and compute the coupled exposure effect. The efficacy of this optimization method is tested for a variety of setup configurations that involve multi-wavelength illumination, two-photon absorption, and time-multiplexed scanning beam. A special test case of holo-tomographic patterning optimized 64 holograms simultaneously and achieved the lowest error among all demonstrations. This variant of tomographic VAM shows promises for achieving high-contrast microscale fabrication. All testing results indicate that a fully coupled optimization offers superior solutions relative to a decoupled optimization approach.
Component inspection is often the bottleneck in high-value manufacturing, driving industries like aerospace toward automated inspection technologies. Current systems often employ fixed arm robots, but they lack the flexibility in adapting to new components or orientations Advanced mobile robotic platforms with updated sensor technologies and algorithms have improved localization and path planning capabilities, making them ideal for bringing inspection processes directly to parts. However, mobile platforms introduce challenges in localization and maneuverability, leading to potential errors. Their positional uncertainty is higher than fixed systems due to the lack of a fixed calibrated location, posing challenges for position-sensitive inspection sensors. Therefore, it's essential to assess the positional accuracy and repeatability of mobile manipulator platforms. The KUKA KMR iiwa was chosen for its collaborative features, robust build, and scalability within the KUKA product range. The accuracy and repeatability of the mobile platform were evaluated through a series of tests to evaluate the performance of its integrated feature mapping, the effect of various speeds on positional accuracy, and the efficiency of the omnidirectional wheels for a range of translation orientations. Experimental evaluation revealed that enabling feature mapping substantially improves the KUKA KMR iiwa's performance, with accuracy gains and error reductions exceeding 90%. Repeatability errors were under 7 mm with mapping activated and around 2.5 mm in practical scenarios, demonstrating that mobile manipulators, incorporating both the manipulator and platform, can fulfil the precise requirements of industries with high precision needs. Providing a highly diverse alternative to traditional fixed-base industrial manipulators.
Olivier Absil, Matthew Kenworthy, Christian Delacroix
et al.
The Mid-infrared ELT Imager and Spectrograph (METIS) is one of the first-generation scientific instruments for the ELT, built under the supervision of ESO by a consortium of research institutes across and beyond Europe. Designed to cover the 3 to 13 $μ$m wavelength range, METIS had its final design reviewed in Fall 2022, and has then entered in earnest its manufacture, assembly, integration, and test (MAIT) phase. Here, we present the final design of the METIS high-contrast imaging (HCI) modes. We detail the implementation of the two main coronagraphic solutions selected for METIS, namely the vortex coronagraph and the apodizing phase plate, including their combination with the high-resolution integral field spectrograph of METIS, and briefly describe their respective backup plans (Lyot coronagraph and shaped pupil plate). We then describe the status of the MAIT phase for HCI modes, including a review of the final design of individual components such as the vortex phase masks, the grayscale ring apodizer, and the apodizing phase plates, as well as a description of their on-going performance tests and of our plans for system-level integration and tests. Using end-to-end simulations, we predict the performance that will be reached on sky by the METIS HCI modes in presence of various environmental and instrumental disturbances, including non-common path aberrations and water vapor seeing, and discuss our strategy to mitigate these various effects. We finally illustrate with mock observations and data processing that METIS should be capable of directly imaging temperate rocky planets around the nearest stars.
Image-based systems have gained popularity owing to their capacity to provide rich manufacturing status information, low implementation costs and high acquisition rates. However, the complexity of the image background and various anomaly patterns pose new challenges to existing matrix decomposition methods, which are inadequate for modeling requirements. Moreover, the uncertainty of the anomaly can cause anomaly contamination problems, making the designed model and method highly susceptible to external disturbances. To address these challenges, we propose a two-stage strategy anomaly detection method that detects anomalies by identifying suspected patches (Ano-SuPs). Specifically, we propose to detect the patches with anomalies by reconstructing the input image twice: the first step is to obtain a set of normal patches by removing those suspected patches, and the second step is to use those normal patches to refine the identification of the patches with anomalies. To demonstrate its effectiveness, we evaluate the proposed method systematically through simulation experiments and case studies. We further identified the key parameters and designed steps that impact the model's performance and efficiency.
Predicting mechanical properties in metal additive manufacturing (MAM) is essential for ensuring the performance and reliability of printed parts, as well as their suitability for specific applications. However, conducting experiments to estimate mechanical properties in MAM processes can be laborious and expensive, and they are often limited to specific materials and processes. Machine learning (ML) methods offer a more flexible and cost-effective approach to predicting mechanical properties based on processing parameters and material properties. In this study, we introduce a comprehensive framework for benchmarking ML models for predicting mechanical properties. We compiled an extensive experimental dataset from over 90 MAM articles and data sheets from a diverse range of sources, encompassing 140 different MAM data sheets. This dataset includes information on MAM processing conditions, machines, materials, and resulting mechanical properties such as yield strength, ultimate tensile strength, elastic modulus, elongation, hardness, and surface roughness. Our framework incorporates physics-aware featurization specific to MAM, adjustable ML models, and tailored evaluation metrics to construct a comprehensive learning framework for predicting mechanical properties. Additionally, we explore the Explainable AI method, specifically SHAP analysis, to elucidate and interpret the predicted values of ML models for mechanical properties. Furthermore, data-driven explicit models were developed to estimate mechanical properties based on processing parameters and material properties, offering enhanced interpretability compared to conventional ML models.
Light guide plates are essential optical components widely used in a diverse range of applications ranging from medical lighting fixtures to back-lit TV displays. In this work, we introduce a fully-integrated, high-throughput, high-performance deep learning-driven workflow for light guide plate surface visual quality inspection (VQI) tailored for real-world manufacturing environments. To enable automated VQI on the edge computing within the fully-integrated VQI system, a highly compact deep anti-aliased attention condenser neural network (which we name LightDefectNet) tailored specifically for light guide plate surface defect detection in resource-constrained scenarios was created via machine-driven design exploration with computational and "best-practices" constraints as well as L_1 paired classification discrepancy loss. Experiments show that LightDetectNet achieves a detection accuracy of ~98.2% on the LGPSDD benchmark while having just 770K parameters (~33X and ~6.9X lower than ResNet-50 and EfficientNet-B0, respectively) and ~93M FLOPs (~88X and ~8.4X lower than ResNet-50 and EfficientNet-B0, respectively) and ~8.8X faster inference speed than EfficientNet-B0 on an embedded ARM processor. As such, the proposed deep learning-driven workflow, integrated with the aforementioned LightDefectNet neural network, is highly suited for high-throughput, high-performance light plate surface VQI within real-world manufacturing environments.
Additive manufacturing parameters of high-performance polymers greatly affect the thermal history and consequently quality of the end-part. For fused deposition modeling (FDM), this may include printing speed, filament size, nozzle, and chamber temperatures, as well as build plate temperature. In this study, the effect of thermal convection inside a commercial 3D printer on thermal history and crystalline morphology of polyetheretherketone (PEEK) was investigated using a combined experimental and numerical approach. Using digital scanning calorimetry (DSC) and polarized optical microscopy (POM), crystallinity of PEEK samples was studied as a function of thermal history. In addition, using finite element (FE) simulations of heat transfer, which were calibrated using thermocouple measurements, thermal history of parts during virtual 3D printing was evaluated. By correlating the experimental and numerical results, the effect of printing parameters and convection on thermal history and PEEK crystalline morphology was established. It was found that the high melting temperature of PEEK, results in fast melt cooling rates followed by short annealing times during printing, leading to relatively low degree of crystallinity (DOC) and small crystalline morphology.
This paper presents I-nteract, a cyber-physical system that enables real-time interaction with real and virtual objects in a mixed augmented reality environment to design 3D models for additive manufacturing. The system has been developed using mixed reality technologies such as HoloLens, for augmenting visual feedback, and haptic gloves, for augmenting haptic force feedback. The efficacy of the system has been demonstrated by generating 3D model using a novel scanning method to 3D print a customized orthopedic cast for human arm, by estimating spring rates of compression springs, and by simulating interaction with a virtual spring using hand.
Shailesh Tripathi, David Muhr, Brunner Manuel
et al.
The implementation of robust, stable, and user-centered data analytics and machine learning models is confronted by numerous challenges in production and manufacturing. Therefore, a systematic approach is required to develop, evaluate, and deploy such models. The data-driven knowledge discovery framework provides an orderly partition of the data-mining processes to ensure the practical implementation of data analytics and machine learning models. However, the practical application of robust industry-specific data-driven knowledge discovery models faces multiple data-- and model-development--related issues. These issues should be carefully addressed by allowing a flexible, customized, and industry-specific knowledge discovery framework; in our case, this takes the form of the cross-industry standard process for data mining (CRISP-DM). This framework is designed to ensure active cooperation between different phases to adequately address data- and model-related issues. In this paper, we review several extensions of CRISP-DM models and various data-robustness-- and model-robustness--related problems in machine learning, which currently lacks proper cooperation between data experts and business experts because of the limitations of data-driven knowledge discovery models.
Thomas G. Gallmeyer, Senthamilaruvi Moorthy, Branden B. Kappes
et al.
Dislocation structures, chemical segregation, {γ^{\prime}, {γ^{\prime \prime}}, δ precipitates and Laves phase were quantified within the microstructures of Inconel 718 (IN718) produced by laser powder bed fusion additive manufacturing (AM) and subjected to standard, direct aging, and modified multi-step heat treatments. Additionally, heat-treated samples still attached to the build plates vs. those removed were also documented for a standard heat treatment. The effects of the different resulting microstructures on room temperature strengths and elongations to failure is revealed. Knowledge derived from these process structure property relationships was used to engineer a super solvus solution anneal at 1020 degC for 15 minutes, followed by aging at 720 degC for 24 hours heat treatment for AM-IN718 that eliminates Laves and δ phases, preserves AM specific dislocation cells that are shown to be stabilized by MC carbide particles, and precipitates dense {γ^{\prime} and {γ^{\prime \prime}} nanoparticle populations. This 'optimized for AM-IN718 heat treatment' results in superior properties relative to wrought/additively manufactured, then industry standard heat treated IN718: relative increases of 7/10 percent in yield strength, 2/7 percent in ultimate strength, and 23/57 percent in elongation to failure are realized, respectively, regardless of as-built vs. machined surface finishes.
Laser-based additive manufacturing offers a promising route for 3D printing of metallic parts. We evidence experimentally a particular columnar solidification microstructure in a Laser Powder-Bed Fusion processed Inconel 718 nickel-based alloy, that we interpret using phase-field simulations and classical dendritic growth theories. Owing to the large temperature gradient and cooling rate, solidification takes places through dendritic arrays wherein the characteristic length scales, i.e tip radius, diffusion length and primary spacing, are of the same order. This leads to a weak mutual interaction between dendrite tips, and a drastic reduction of side-branching. The resulting irregular cellular-like solidification pattern then remains stable on time scales comparable to the complete melt pool solidification, as observed in the as-built material.
Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.