Search Results (17)

To address the limitation of 2D methods in inferring absolute scrap dimensions from images, we propose Scrap-SAM-CLIP (SSC), a vision-language model integrating the segment anything model (SAM) and contrastive language-image pre-training in Chinese (CN-CLIP). The model enables identification of canonical scrap shapes, establishing a foundational framework for subsequent 3D reconstruction and dimensional extraction within the 3D recognition pipeline. Individual modules of SSC are fine-tuned on the self-constructed scrap dataset. For segmentation, the combined box-and-point prompt yields optimal performance among various prompting strategies. MobileSAM and SAM-HQ-Tiny serve as effective lightweight alternatives for edge deployment. Fine-tuning the SAM decoder significantly enhances robustness under noisy prompts, improving accuracy by at least 5.55% with a five-positive-points prompt and up to 15.00% with a five-positive-points-and-five-negative-points prompt. In classification, SSC achieves 95.3% accuracy, outperforming Swin Transformer V2_base by 2.9%, with t-SNE visualizations confirming superior feature learning capability. The performance advantages of SSC stem from its modular assembly strategy, enabling component-specific optimization through subtask decoupling and enhancing system interpretability. This work refines the scrap 3D identification pipeline and demonstrates the efficacy of adapted foundation models in industrial vision systems. Full article

In the framework of high temperature components, the need to evaluate the accumulated creep damage during service life is fundamental to extend the life of components which are currently deemed as scrap as per design intent. Thus, the life assessment of Ni-based superalloys could be performed in relation to the accumulated creep deformation which represents the limiting factor for serviced components. Despite the different microstructural changes that occur in service life, this work focuses on the possibility to evaluate the material strain by means of electron backscattered diffraction (EBSD). The key point is the identification of the correlation between geometrically necessary dislocation (GND) density derived from EBSD analyses and the reached creep strain for a single crystal Ni-based superalloy. However, the results of GND density are affected by the settings’ parameters adopted to perform the analysis by the magnification level and the step size. These two parameters have been optimized by analyzing specimens from interrupted creep tests at strain levels between 0.5% and 10%, in the temperature range between 850 °C and 1000 °C. Full article

Driven by environmental concerns and aligned with the principles of the circular economy, urban plastic waste—including packaging materials, disposable items, non-functional objects, and industrial scrap—is increasingly being collected, recycled, and marketed as a potential substitute for virgin polymers. However, the use of recycled polymers introduces uncertainties that can significantly affect both the durability and the further recyclability of the resulting products. This paper demonstrates how spectroscopic analysis in the mid-infrared (MIR) and near-infrared (NIR) regions can be applied well beyond the basic identification of the main polymeric component, typically performed during the sorting stage of recycling processes. A detailed interpretation of spectral data, based on well-established correlations between spectroscopic response and material structure, enables the classification of recycled polymers according to specific physicochemical properties, such as chemical composition, molecular architecture, and morphology. In this context, infrared spectroscopy not only provides a reliable comparison with the corresponding virgin polymer references but also proves particularly effective in assessing the homogeneity of recycled materials and the reproducibility of their properties—factors not inherently guaranteed due to the variability of input sources. As a case study, we present a robust protocol for determining the polypropylene content in recycled polyethylene samples. Full article

In this study, we adopt a geometallurgical analytical approach common in mineral processing in the characterization of samples of shredded waste printed circuit board (PCB) E-waste, originating from Europe. Conventionally, bulk chemical analysis provides a value for E-waste; however, chemical analysis alone does not provide information on the textural variability, phase complexity, grain size, particle morphology, phase liberation and associations. To address this, we have integrated analysis using binocular microscopy, manual scanning electron microscopy, phase, textural and compositional analyses by automated (SEM-EDS), phase analysis based on (Automated Material Identification and Classification System (AMICS) software, and elemental analysis using micro-XRF. All methods used have strengths and limitations, but an integration of these analytical tools allows the detailed characterization of the texture and composition of the E-waste feeds, ahead of waste reprocessing. These data can then be used to aid the design of optimized processing circuits for the recovery of the key payable components, and assist in the commercial trading of e-scrap. Full article

The widespread scrapping of retired mechanical parts has led to severe waste of resources and environmental burdens, posing a significant challenge to sustainable industrial development. To enable efficient recycling of retired mechanical parts and enhance the sustainability of their remanufacturing processes, the concept of biological genes is adopted to characterize the changes in the information of retired mechanical parts during the remanufacturing process as gene mutations of parts, aiming to maximize remanufacturing potential and devise an optimal generalized remanufacturing strategy for extending part life cycles. However, gene mutation of retired mechanical parts is not an isolated event. The modification of local genes may disrupt the original equilibrium of the part’s state, leading to conflicts such as material–performance, structure–function/performance, and function–performance. These conflicts constitute a major challenge and bottleneck in designing generalized remanufacturing schemes. Therefore, we propose a conflict identification and resolution method for gene mutation of retired mechanical parts. First, gene mutation graph of retired mechanical parts is established to express its all-potential remanufacturing pathways. Using discrimination rules and the element representation method from extenics, mutation conflicts are identified, and a conflict problem model is constructed. Then, the theory of inventive problem solving (TRIZ) engineering parameters are reconstructed and mapped to the mutation conflict parameters. The semantic mapping between the inventive principles and the transforming bridges is established by the Word2Vec algorithm, thereby improving the transforming bridge method to generate conflict resolution solutions. A coexistence degree function of transforming bridges is proposed to verify the feasibility of the resolution solutions. Finally, taking the generalized remanufacturing of a retired gear shaft as an example, we analyze and discuss the process and outcome of resolving gene mutation conflicts, thereby verifying the feasibility and effectiveness of the proposed concepts and methodology. Full article

In discussions on environmental policies, eco-efficiency is often underlined. Eco-efficiency is defined as delivering products and services with competitive value while simultaneously reducing the ecological impacts and meeting human needs. In highly competitive industrial environments, improvements in production processes are crucial for maintaining a strong differentiated position and competitive ability. Additionally, rationalizing energy consumption and optimizing the use of natural resources are essential for sustainability. This work presents an empirical study of a Portuguese industrial company focused on minimizing scrap production in extrusion processes. This is a common challenge in industrial extrusion processes worldwide, with significant economic and environmental implications. A literature review revealed strong relationships between key extrusion process parameters, including temperature, time, speed, pressure, and geometry. The main objective of this work is to model the aluminum extrusion process in a simple and replicable way, avoiding complex models such as nonlinear optimization or finite element methods, with a view toward potential machine learning applications for scrap reduction. Thus, simple multiple linear regression models enable the identification of the most influential variables involved in the process. The results identify key variables that impact scrap generation, aligning with findings from the literature. In this dataset, geometry-related factors are the parameters with notable scrap rates. Full article

Hospital buildings require special attention to protect patients and healthcare workers from hospital-acquired infections and sick building illnesses. This is the first study to assess the prevalence of fungus in indoor air, outdoor air, and their contamination on surfaces at selected locations in four highly contaminated hospitals (A, B, C, and D) in Peninsular Malaysia. A total of 294 indoor air samples, 106 scrapped and 169 swabbed, were collected from July 2019 to August 2020. Bioaerosol concentrations were calculated using the colony-forming unit (CFU)/m³. Molecular identification was performed on the cultures. The internal transcribed spacer (ITS) region in the rRNA gene of the isolates was amplified by PCR. Results showed that fungal burden was in the range between 18 and 2597 CFU/m³. Fungal load in selected locations at Hospital D were in the higher range between 106 and 2597 CFU/m³, with two locations exceeding the national guidelines. Fungal genera were highly identified in air samples (47) compared to swabbed (29) and scrapped (18) samples. The dominant species were C. halotolerans, C. tenuissimum, P. alfredii, P. brevicompactum, P. brocae, P. cataractarum, and A. aculeatus. Fungal loads were higher in the Orthopedic and Oral Surgeon Clinic, the On Call Emergency Room, wards, and pathways. Full article

Artificial intelligence (AI) has become a revolutionary tool in the automotive sector, specifically in quality management and issue identification. This article presents a systematic review of AI implementations whose target is to enhance production processes within Industry 4.0 and 5.0. The main methods analyzed are deep learning, artificial neural networks, and principal component analysis, which improve defect detection, process automation, and predictive maintenance. The manuscript emphasizes AI’s role in live auto part tracking, decreasing dependance on manual inspections, and boosting zero-defect manufacturing strategies. The findings indicate that AI quality control tools, like convolutional neural networks for computer vision inspections, considerably strengthen fault identification precision while reducing material scrap. Furthermore, AI allows proactive maintenance by predicting machine defects before they happen. The study points out the importance of incorporating AI solutions in actual manufacturing methods to ensure consistent adaptation to Industry 5.0 requirements. Future investigations should prioritize transparent AI approaches, cyber-physical system consolidation, and AI material enhancement for sustainable production. In general terms, AI is changing quality assurance in the automotive industry, improving efficiency, consistency, and long-term results. Full article

This research aims to propose a novel approach for evaluating and minimizing scraps in an industrial production of premium food cans with distortion printing. Beyond conventional formability criteria, a waving requirement is introduced to ensure aesthetic quality of the printed graphics. The research focuses on real production conditions, specifically involving double-cold-reduced (DR) low-carbon steel sheets and chromium-coated tin-free steel with a thickness of 0.16 mm. The sheets are laminated on both sides with a plastic film prior to undergoing distortion printing on the exterior. Subsequently, a blank is subjected to a drawing-redrawing process to form a food can. To address challenges associated with characterizing these thin sheets, a material parameter identification method is proposed and demonstrated. The thickness profile and flange length are identified as key criteria for this identification process. Measurements of thickness distribution and flange length are obtained using digital image correlation (DIC) and microscopy techniques. Within the manufacturing system, uncertainties related to material properties and forming processes can result in scraps or defects. To analyze these processes, finite element analysis (FEA) is employed and validated through experiments. For the evaluation of scrap rates, uncertainty propagation is conducted using a metamodeling technique, specifically employing radial basis function (RBF) neural networks. The study concludes by offering process optimization recommendations aimed at reducing the scrap rate. Full article

Transitioning from a traditional linear economy to a circular economy occurs at the micro-level system, encompassing products and companies, which should be monitored. For metals, recycled content as an input-side indicator of recycling quantifies the ratio of metal scrap consumed during production and fabrication. However, conventional methodology struggles to evaluate recycled content uniquely due to the ambiguous classification of new scrap derived from industrial processes. Additionally, the input and output of new scrap between micro-level systems are often inadequately counted, causing inconsistencies in the recognition of secondary input between macro- and micro-level systems. This study introduces a refined classification for metal scrap, precisely distinguishing new scrap by its originating processes. Furthermore, we propose a novel perspective on new scrap, viewing it as a mixture of old scrap and primary raw materials, with only the portion of old scrap being considered secondary raw material. This stance navigates past the binary classification—whether new scrap should be classified as secondary—eliminating ambiguity and allowing for clear identification of secondary raw materials. The developed methodology ensures that all inputs of scrap are accounted for without leakage, and the recycled content of a specific metal is uniquely determined, maintaining consistency with macro-level systems. Full article

In the coupled pickling line and tandem cold mill (PL-TCM), the hot-rolled strip needs to be trimmed on both sides of the strip before the tandem cold rolling process to ensure stable operation of the rolling process. The equipment for trimming the strip is the side trimmer, and during trimming a failure of the side scrap blockage is often caused by the variation in the width of the hot-rolled strip and the deviation during the actual operation. For this problem, this paper established a finite element model of strip trimming by side trimmer, analyzed the influence of side scrap width, structure parameters, and strip specifications on the equivalent plastic strain at the trimmed position of the strip, and obtained the influence law of each factor during the trimming process. On this basis, by collecting the historical data of side scrap blockage failure of the side trimmer, the threshold value of the side scrap width setting is obtained. Combining the width data of the hot-rolled strip and the actual operation status monitoring of the strip in the inlet section of the PL-TCM, the side scrap blockage risk identification function and the speed reduction strategy of the side trimmer are designed to form the side scrap blockage pre-control model together. After applying the side scrap blockage pre-control model to a PL-TCM, a 40.5% reduction in side scrap blockage failures was achieved compared with the same length of time before the application, which achieved satisfactory results. Full article

During the secondary production of aluminum, upon melting the scrap in a furnace, there is the possibility of developing an aluminothermic reaction, which produces oxides in the molten metal bath. Aluminum oxides must be identified and removed from the bath, as they modify the chemical composition and reduce the purity of the product. Furthermore, accurate measurement of molten aluminum level in a casting furnace is crucial to obtain an optimal liquid metal flow rate which influences the final product quality and process efficiency. This paper proposes methods for the identification of aluminothermic reactions and molten aluminum levels in aluminum furnaces. An RGB Camera was used to acquire video from the furnace interior, and computer vision algorithms were developed to identify the aluminothermic reaction and melt level. The algorithms were developed to process the image frames of video acquired from the furnace. Results showed that the proposed system allowed the online identification of the aluminothermic reaction and the molten aluminum level present inside the furnace at a computation time of 0.7 s and 0.4 s per frame, respectively. The advantages and limitations of the different algorithms are presented and discussed. Full article

The aim of this case study is to implement the Lean Six Sigma methodology to reduce the scrap rate of the edge-bending process of a metal door case used in the assembly process of refrigeration appliances. This study was initiated because the assembly process of refrigerators does not work at maximum capacity due to the scrap that occurs for this component. Losses have direct effects on a company’s profits and on its competitiveness on the market. This research provides an overview of the identification of the most optimal and useful tools that can be used in each context; this will help to establish a protocol which can be applied in similar contexts. Although this study is limited to one process, the results will have direct effects on the assembly line of the organization. The purpose of this study is to increase the capability of the process and to improve the efficiency of the delivery of the component parts to the assembly line. This case study provides further evidence of the effectiveness of the use of the Six Sigma methodology in identifying and reducing scrap rates. Full article

In order to reduce the cost of lithium-ion batteries, production scrap has to be minimized. The reliable detection of electrode defects allows for a quality control and fast operator reaction in ideal closed control loops and a well-founded decision regarding whether a piece of electrode is scrap. A widely used inline system for defect detection is an optical detection system based on line scan cameras and specialized lighting. The cameras scan the electrode, and brightness differences on the surface are detected and processed inline. The characteristics of the defect image are used for automated classification of the defects based on image features. Furthermore, the detailed detection of defects allows for the identification of causes. This paper describes the working principle of such an inline detection system, the catalog of typical defects, and the image features used to classify them automatically. Furthermore, we propose and discuss causes and effects of the different defect types on the basis of the literature and expert experience. In combination with tracking and tracing, this enables the manufacturer to reduce scrap by detecting defects early in the production chain. Full article

In order to reduce the elemental species produced in the recycling and melting of aluminum scrap and to improve the quality of pure aluminum and aluminum alloys, it is necessary to classify the different grades of aluminum scrap before melting. For the problem of classifying different grades of aluminum scrap, most existing studies are conducted using laser-induced breakdown spectroscopy for identification and classification, which requires a clean and flat metal surface and enormous equipment costs. In this study, we propose a new classification and identification method for different grades of aluminum scrap based on the ResNet18 network model, which improves the identification efficiency and reduces the equipment cost. The objects of this research are three grades of aluminum scrap: 1060, 5052, and 6061. The surface features of the three grades were compared using a machine vision algorithm; three different datasets, using RGB, HSV, and LBP, were built for comparison to find the best training dataset for subsequent datasets, and the hyperparameters of learning rate and batch size were tuned for the ResNet18 model. The results show that there was a differentiation threshold between different grades through the comparison of surface features; the ResNet18 network model trained the three datasets, and the results showed that RGB was the best dataset. With hyperparameter optimization of the ResNet18 model, the accuracy of final classification and recognition could reach 100% and effectively achieve the classification of different grades of aluminum scrap. Full article