Computers in Industry最新文献

This preliminary research presents a comparative study between Text-to-Image AI models and Shape Grammars, one of the main generative approaches to Computer Aided Conceptual Design. The goal is to determine to which extent AI models can reproduce or complement the performance of grammar algorithms as creative support tools for shape exploration in conceptual product design. Workflows, advantages and limitations are identified through a comprehensive practical comparison example. The results show many similarities regarding generative capabilities and highlight several advantages of Text-to-Image AI models, including an easier way of capturing product grammars and a wider and more immediate range of further applications. In contrast, Shape Grammars approach proved more solid in aspects related to exploration workflows and cognitive stimulation. These results encourage the research on new ways to address the interaction between designers and AI generative models, combining the AI potential with well-established generative strategies.

This paper delves into the accurate detection of the early initial degradation point (IDP) in bearings, and proposes, for the first time, a comprehensive adaptive IDP detection framework for bearings under variable operating conditions, along with an outlier data repair strategy. First, this study introduces the adaptive early initial degradation point detection (AEIDPD) method, which incorporates least-squares fitting to compute the slope and intercept of health indicators, and t-tests are used to construct the “sum-of-slopes” indicator. An adaptive IDP threshold construction method that adapts to variable operating conditions is proposed, establishing a strategy for IDP detection based on sum-of-slopes and adaptive thresholds. To enhance the robustness of AEIDPD in variable operating conditions, this paper introduces synchronized wavelet transform to obtain the "synchronous pseudo-speed" signal of bearing vibration, and constructs a condition interference elimination strategy based on velocity and sliding window averaging to mitigate the effects of variable operating conditions. Additionally, the study constructs upper and lower bounds for the root mean square feature of vibration signals using empirical parameters to correct outliers, providing more accurate data to support bearing life predictions. Experimental results demonstrate the effectiveness and robustness of the proposed methods.

Engineering fault diagnosis often needs to be implemented without prior knowledge of labels. Considering the randomness and drift of fault features, this paper proposes fusing multichannel autoencoders with dynamic global loss (FMA-DGL) to enhance self-supervised fault diagnosis. Multiple autoencoders are employed to represent the fault features of multichannel vibration signals. A dynamic global loss function is utilized to self-supervise the generation of pseudo-labels, thereby integrating multichannel feature information together. The proposed dynamic global loss controls the degree of conflict of samples from different channels to construct clustering centers, allowing the clustering process to converge more smoothly. By leveraging both the common and complementary information across different channels, the randomness and drift issues of self-supervised pseudo-labels are addressed, effectively enhancing the fault diagnosis performance through multichannel fusion. Experiments were carried out using a public bearing dataset and a rotating machinery experimental setup, respectively. Results show that the proposed FMA-DGL outperforms the state-of-the-art peer methods, exhibiting good results and applicability in self-supervised fault diagnosis based on multichannel vibration signals.

The crude oil price has been subject to periodic fluctuations because of seasonal changes in industrial demand and supply, weather, natural disasters and global political unrest. An accurate forecast of crude oil prices is of utmost importance for decision makers and industry players in the energy sector. Despite this, the volatility of crude oil prices contributes to the uncertainty of the energy industry, which was particularly challenging following the recent global spread of the COVID-19 epidemic and the Russia–Ukraine conflict. This paper proposes a hybrid deep learning (DL) modelling framework to deal with the volatility of crude oil prices, applying ensemble empirical mode decomposition (EEMD), convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) integrated with quantile regression (QR); named EEMD-CNN-BiLSTM-QR. Two real-world datasets on crude oil prices from the West Texas Intermediate and Brent Crude Oil markets were employed to validate the EEMD-CNN-BiLSTM-QR hybrid modelling framework. Given that the probability density forecast can capture uncertainty, an in-depth analysis was carried out and prediction accuracy calculated. The findings of this study demonstrate that the proposed EEMD-CNN-BiLSTM-QR DL modelling framework, which uses the probability density forecast method, is superior to other tested models in terms of its ability to forecast crude oil prices. The novelty of this study stems mainly from its use of QR, which allows for the description of the conditional distribution of predicted variables and the extraction of more uncertain information for probability density forecasts.

The methods for unsupervised visual inspection use algorithms that are developed, trained and evaluated on publicly available datasets. However, these datasets do not reflect genuine industrial conditions, and thus current methods are not evaluated in real-world industrial production contexts. To answer this shortcoming, we introduce AutoVI, an industrial dataset of visual defects that can be encountered on automotive assembly lines. This dataset, comprising six inspection tasks, was designed as a benchmark to assess the performance of defect detection methods under realistic acquisition conditions. We analyze the performance of current state-of-the-art methods and discuss the difficulties specifically encountered in the industrial context. Our results show that current methods leave considerable room for improvement. We make AutoVI publicly available to develop unsupervised detection methods that will be better suited to real industrial tasks.

Digitally enhanced technologies are transforming every aspect of the manufacturing sector towards the era of digital manufacturing. Traditional lubricant development methods involving systematic but time-consuming iterative processes is still extensively used in the metal forming industry. In the present study, a novel digitally enhanced lubricant development scheme was proposed by leveraging a mechanism-based interactive friction modelling framework and quantitative and comprehensive evaluation of lubricant performance via the data-centric lubricant limit diagrams. By predicting transient lubricant behaviour following the complex contact condition evolution experienced in actual forming operations, a close association and quantified relation between the lubricant performance and its properties such as viscosity, evaporation rate and fraction of dry matter was established. This can facilitate the optimisation efficiency of lubricant parameters and minimise the experimental cost for iterative lubricant trials. A case study was conducted in this work to develop a customised lubricant using this digitally enhance scheme for the target hot stamping process based on a benchmark lubricant as a reference. Further industrial forming tests of an automotive component were conducted to validate the ideal performance of the customised lubricant.

In industrial sectors such as shipping, chemical processing, and energy production, centrifugal pumps often experience failures due to harsh operational environments, making it challenging to accurately identify fault types. Traditional fault diagnosis methods, which heavily rely on existing fault datasets, suffer from limited generalization capabilities, especially when substantial labeled and specific fault sample data are lacking. This paper proposes a novel fault diagnosis approach for centrifugal pumps, utilizing a digital twin (DT) framework powered by a graph transfer learning model to address this issue. Firstly, a high-fidelity DT model is constructed to simulate the flow-induced vibration response of the impeller under different health states to enrich the type and scale of the dataset. Secondly, a graph convolutional neural networks (GCN) model is constructed to learn the knowledge of simulation data, and the Wasserstein distance between simulation data and measured data is optimized for adversarial domain adaptation, thereby achieving efficient cross-domain fault diagnosis. Experimental results demonstrate that the proposed algorithm delivers effective fault diagnosis with minimal prior knowledge and outperforms comparable models. Furthermore, the DT system developed using the proposed model enhances the operational reliability of centrifugal pumps, reduces maintenance costs, and presents an innovative application of DT technology in industrial fault diagnosis.

The accuracy and quality of part formation are crucial considerations. However, the laser directed energy deposition (L-DED) process often leads to irregular changes in deposition contours and mechanical properties across parts due to complex flow fields and temperature variations. Hence, to ensure the forming accuracy and quality, it is necessary to achieve precise monitoring and appropriate parameter adjustments during the processing. In this study, a machine vision method for real-time monitoring is proposed, which combines target tracking and image processing techniques to achieve accurate recognition of deposition contours under noisy conditions. Through comparative verification, the measurement accuracy reaches as high as 98.98 %. Leveraging the monitoring information, a bidirectional prediction neural network is proposed to accomplish layer-by-layer forward prediction of layer height. Meanwhile, inverse prediction is employed to determine the processing parameters required for achieving the desired layer height, facilitating the optimization of the deposition contours. It was found that as the processing parameters were adjusted layer-by-layer to achieve consistent deposition contours, there was also a tendency towards consistent changes in microstructure and mechanical properties. The standard deviations of primary dendrite arm spacing (PDAS) and ultimate tensile strength (UTS) at different positions decrease by over 52.2 % and 61.4 %, respectively. This study reveals the consistent patterns of variation in deposition contours and mechanical properties under data-driven variable parameter processing, laying an important foundation for future exploration of the complex process-structure-performance (PSP) relationship in L-DED.

Improvements in the performance and graphical quality of Head-Mounted Displays (HMDs) have led to their increasing use in Virtual Reality (VR) for product presentation and virtual prototype (VP) evaluations. Various locomotion techniques in VR make it possible to move through a virtual scenario and approach the VP for evaluation purposes. The integration of eye-tracking devices into recent HMDs allows the trajectory and gaze behavior of observers to be reported during the evaluation, often more objectively than self-report questionnaires. However, very few studies have used physiological measures for the evaluation of products embedded in VR environments. Therefore, this paper offers a study in which 95 people evaluated three VPs of street furniture presented in their environment of use using Meta Quest Pro headset and explored through teleport and natural walking. The influence of the locomotion techniques on the ratings recorded using a semantic differential, sense of presence, cybersickness, and the role of eye-tracking in understanding gaze behavior while evaluating products' Areas of Interest (AOIs), are investigated. This study found no evidence that the way of approaching the product influences the evaluation of some of its features, overall product evaluation, confidence in responses, sense of presence, or cybersickness differently. On the other hand, this work evidences that the locomotion technique had an impact on how the user approached the products, which could significantly influence the viewing time of some AOIs. The study revealed that the most observed AOIs coincided with those parts closely related to important features, generally located at the top of the products, so paying special attention to these parts when designing and evaluating similar VPs is recommended.

A metal tube system is known as the industrial blood vessel, among which the bent section is the most vulnerable part. The cross-sectional defects (CSDs) of the bent tube cause the flow fluctuation of the fluid inside the tube. The existing defect characterization methods are roughly presented by describing CSDs in some specific cross-sections, which results in the lack of the tube full-bent section (FBS) characteristic information. To comprehensively describe and predict the tube FBS characteristics, an advanced physics-embedded CSDs prediction framework is proposed. This framework includes an FBS-neutral layer displacement angle (NLDA) prediction module and an FBS-CSDs prediction module, which uses the method that integrates the analytical model and BiLSTM-based deep learning (DL) models to predict the CSDs in the FBS of the tube. A novel analytical model of CSDs that considers both three-directional stresses and strains during tube bending is embedded in the FBS-CSDs prediction module. The analytical model provides the initial predicted values of CSDs through the NLDA sequence obtained from the FBS-NLDA module. The inaccurate CSDs are then treated as physical information to be fed into DL models for further correction and prediction. The prediction performance of this framework is validated through numerical simulations and experiments. The results prove that the framework can accurately predict the CSDs in the tube FBS. The integration of DL models with the analytical model not only overcomes the limitations of the analytical model, but also improves the prediction accuracy and convergence speed of DL models.