Data-driven Model Research Articles

Modeling and analysis of nonlinear dynamics of axisymmetric vector nozzle based on deep neural network

Abstract The axisymmetric nozzle mechanism is the core part for thrust vectoring of aero engine, which contains complex rigid-flexible coupled multibody system with joints clearance and significantly reduces the efficiency in modeling and calculation, therefore the kinematics and dynamics analysis of axisymmetric vectoring nozzle mechanism based on deep neural network is proposed. The deep neural network model of the axisymmetric vector nozzle is established according to the limited training data from the physical dynamic model and then used to predict the kinematics and dynamics response of the axisymmetric vector nozzle. This study analyses the effects of joint clearance on the kinematics and dynamics of the axisymmetric vector nozzle mechanism by a data-driven model. It is found that the angular acceleration of the expanding blade and the driving force are mostly affected by joint clearance followed by the angle, angular velocity and position of the expanding blade. Larger joint clearance results in more pronounced fluctuations of the dynamic response of the mechanism, which is due to the greater relative velocity and contact force between the bushing and the pin. Since axisymmetric vector nozzles are highly complex nonlinear systems, traditional numerical methods of dynamics are extremely time-consuming. Our work indicates that the data-driven approach greatly reduces the computational cost while maintaining accuracy, and can be used for rapid evaluation and iterative computation of complex multibody dynamics of engine nozzle mechanism.

A Multi-Objective Energy Optimization Model for Renewable Energy Systems with Hybrid Energy Storage

Building a Renewable Energy System (RES) is a viable way to address resource depletion and accomplish decarbonization. This study presents a hybrid power system that combines wind, solar, battery, and thermal energy storage. It also examines the co-optimization of scheduling and operation for multiple objectives. The hybrid system combines the affordability of thermal energy storage (TES) with the adaptability of batteries to effectively address the issue of intermittent RES. A new approach for integrated operation is offered, which relies on the electrical block's operation limit. The planning-operation co-optimization system considers minimizing the Net Present Cost (NPC) and reducing power supply likelihood todetermine the best operation limit and sizing decision factors. The co-optimization issue is addressed using novel multi-objective decision-making (MO-DM). This approach incorporates the Decision-Maker (DM) preferences data to direct the evolutionary process toward the desired area. In addition, a data-driven prediction model captures the risks and losses associated with wind generation. The case study's findings indicate the following: (1) The data-driven system has a higher level of precision in wind power projection when compared with commonly used physical simulations. (2) The suggested MO-DM exhibits superior integration, variety, and robustness achievement in the DMchosen area compared to others. (3) The combined battery-thermal energy storing structure achieves improved economy and dependability through the optimum organized operation approach, in contrast to using a single energy storage system under various testing constraints.

Data-driven pressure prediction for self-pressurization liquid hydrogen tank using transfer learning method

Prediction of pressure evolution in liquid hydrogen (LH2) tanks utilizing data-driven technology has gradually garnered significant attention. However, training an accurate data-driven model for pressure prediction in LH2 tanks is a challenge due to inadequate experimental data. To end this, this paper presents a Backpropagation Neural Network model for pressure prediction in LH2 tanks based on transfer learning on pre-trained models, using experimental data and results from thermodynamics models. Pre-trained models are firstly optimized by Bayesian optimization algorithms with large sample datasets from the thermal multi-zone model program and then performed the fine-tuning method with small sample datasets from experiments. The effectiveness of the proposed approach is validated by experimental data and numerical results. Compared with baseline models trained only with experimental data, the results demonstrate better model performance, with a maximum of 10.51% accuracy improvement. The proposed approach demonstrates considerable potential in facilitating the application of advanced machine learning algorithms for LH2 tank pressure prediction, significantly reducing the dependence on experimental data collection.

The concept of big data and predictive analytics in reservoir engineering: The future of dynamic reservoir models

Reservoir engineering is a critical discipline in the oil and gas industry, aimed at optimizing the extraction and management of subsurface resources. Traditionally, reservoir models have relied on static data and conventional simulation methods, which often fall short in capturing the dynamic complexities of reservoirs. With the advent of big data and predictive analytics, there is a significant opportunity to revolutionize reservoir modeling by integrating real-time data for continuous updates and more accurate predictions. This review introduces a theoretical exploration of how big data and predictive analytics can transform dynamic reservoir models, highlighting their potential to improve reservoir management and hydrocarbon recovery. Big data technologies enable the collection, storage, and processing of vast amounts of structured and unstructured data from multiple sources, including well logs, seismic surveys, drilling operations, and production data. Predictive analytics, through machine learning and statistical techniques, can extract actionable insights from these datasets to predict reservoir behavior, enhance decision-making, and optimize production strategies. This integration facilitates real-time monitoring and adaptive reservoir management, allowing engineers to respond to changing reservoir conditions and uncertainties more effectively. The review further explores the implications of big data-driven predictive models for enhanced hydrocarbon recovery techniques, such as water flooding and gas injection. By automating data processing and integrating real-time field data, predictive analytics can improve the accuracy of reservoir simulations, reduce downtime, and increase operational efficiency. Ultimately, the future of dynamic reservoir modeling lies in the seamless integration of big data and predictive analytics, providing a pathway to smarter, more sustainable resource management and maximized recovery factors in increasingly complex reservoir environments. Keywords: Big Data, Predictive Analytics, Reservoir Engineering, Dynamic Reservoir, Models.

Characteristic analysis method for integrated multi-parameter hydro-viscous speed control system

Hydro-viscous clutch has become an inevitable choice for special vehicle transmissions. As a nonlinear dynamic system with large lagging link, its timing performance is affected by input rotational speed, lubricating oil temperature and pressure and other factors. However, from the control perspective, the speed regulation law, formation mechanism control characteristics, global model of hydro-viscous speed control system (HSCS) are unclear. To solve these problems, this paper presents a comprehensive analysis of the Hydro-viscous Speed Control System (HSCS), focusing on its steady-state and dynamic speed control characteristics. A data-driven model is established to describe the relationship between input rotational speed, output speed, control oil pressure, and lubricating oil temperature. The findings provide a foundation for optimizing HSCS structure and parameters, enhancing the performance and reliability of such systems in special vehicle transmissions and establishing a temperature-speed control system for special vehicle transmissions.

Generalization Limits of Data-Driven Turbulence Models

AbstractMany industrial applications require turbulent closure models that yield accurate predictions across a wide spectrum of flow regimes. In this study, we investigate how data-driven augmentations of popular eddy viscosity models affect their generalization properties. We perform a systematic generalization study with a particular closure model that was trained for a single flow regime. We systematically increase the complexity of the test cases up to an industrial application governed by a multitude of flow patterns and thereby demonstrate that tailoring a model to a specific flow phenomenon decreases its generalization capability. In fact, the accuracy gain in regions that the model was explicitly calibrated for is smaller than the loss elsewhere. We furthermore show that extrapolation or, generally, a lack of training samples with a similar feature vector is not the main reason for generalization errors. There is actually only a weak correlation. Accordingly, generalization errors are probably due to a data-mismatch, i.e., a systematic difference in the mappings from the model inputs to the required responses. More diverse training sets unlikely provide a remedy due to the strict stability requirements emerging from the ill-conditioned RANS equations. The universality of data-driven eddy viscosity models with variable coefficients is, therefore, inherently limited.

Dynamic Data-Driven Deterioration Model for Sugarcane Shredder Hammers Oriented to Lifetime Extension

Several sugar mills operate as waste-to-energy plants. The shredder is the initial high-energy machine in the production chain and prepares sugarcane. Its hammers, essential spare parts, require continuous replacement. Then, the search for intelligent strategies to extend the lifetime of these hammers is fundamental. This paper presents (a) a dynamic data-driven model for estimating the deterioration and predicting remaining life of the sugarcane shredder hammers during operation, for which the real data of the entering sugarcane flow and the power required to prepare the sugarcane are analyzed, and (b) a management architecture intended for online decision-making assistance to extend the hammers’ life by making a trade-off between the desired lifetime, along with a nominal shredder work satisfaction criterion. The deterioration model is validated with real data achieving an accuracy of 84.41%. The remaining life prognostic is within a confidence zone calculated from the historical sugarcane flow, with a probability close to 99%, fitting a lognormal probability distribution. A numerical example is also provided to illustrate a closed loop control, where the proposed architecture is used to extend the useful life of the hammers during operation, adjusting the incoming sugarcane flow while maintaining the nominal work satisfaction of the shredder.

Investigating the Performance of Data-Driven Ensemble Machine Learning Models in Preliminary Designing Multi-Stage Friction Pendulum Bearings

Over the last few decades, the field of base isolation systems has demonstrated enormous advancements through the innovation of novel systems, and there has been an enhancement in the performance of structures equipped with isolation under conditions of moderate and severe seismic activity. One of the most important systems is the multi-stage friction pendulum, which offers a spectrum of effective pendulums across different regimes, thereby achieving enhanced capability for energy dissipation. The difficulty in designing these bearings at the preliminary stage comes from the fairly long process of trials and errors in selecting the properties of each sliding surface so that the required effective period, effective damping, and displacement capacities are achieved. This study investigates the performance of various data-driven ensemble machine learning models in directly designing multi-stage friction pendulum bearings. Within the context of the analysis, the most recent generation of friction pendulum that has been introduced to the literature, the quintuple friction pendulum, is used as the investigation employs a case to assess the dependability of the design strategy and the efficacy of a multi-output machine learning techniques. In general, the findings of this study have shown that machine learning models provide an accurate way to directly design quintuple friction pendulum isolators and attain the necessary properties of the isolators. The practicality of this research lies in highlighting how machine learning can be applied to considerably expedite the design and optimization of multi-stage friction pendulum bearings and in defining the most suitable machine learning technique to adopt in such tasks.

A Data-Driven Model for Classification of Traditional Chinese Medicine Materials

This paper proposes a data-driven classification model for traditional Chinese medicinal herbs based on mid-infrared spectral data. Addressing the limitations of traditional identification methods when the herbs’ appearance is damaged or incomplete, this study employs machine learning techniques to achieve accurate classification of medicinal herb types through spectral data preprocessing and feature extraction. Firstly, the Savitzky-Golay convolution smoothing method and Standard Normal Variate (SNV) transformation were used for denoising the spectral data. Then, Principal Component Analysis (PCA) was employed to reduce the dimensionality of the high-dimensional spectral data and extract the key features. Finally, the Gaussian Mixture Model (GMM) was applied to cluster the reduced data, categorizing the medicinal herbs into six classes. The results show that this method produces the accurate and stable classification. The constructed model is not only applicable to the classification and origin identification of medicinal herbs but also provides an important reference value for the classification and origin identification of other plant species.

Multi-organ gene expression analysis and network modeling reveal regulatory control cascades during the development of hypertension in female spontaneously hypertensive rat.

Hypertension is a multifactorial disease with stage-specific gene expression changes occurring in multiple organs over time. The temporal sequence and the extent of gene regulatory network changes occurring across organs during the development of hypertension remain unresolved. In this study, female spontaneously hypertensive (SHR) and normotensive Wistar Kyoto (WKY) rats were used to analyze expression patterns of 96 genes spanning inflammatory, metabolic, sympathetic, fibrotic, and renin-angiotensin (RAS) pathways in five organs, at five time points from the onset to established hypertension. We analyzed this multi-dimensional dataset containing ~15,000 data points and developed a data-driven dynamic network model that accounts for gene regulatory influences within and across visceral organs and multiple brainstem autonomic control regions. We integrated the data from female SHR and WKY with published multiorgan gene expression data from male SHR and WKY. In female SHR, catecholaminergic processes in the adrenal gland showed the earliest gene expression changes prior to inflammation-related gene expression changes in the kidney and liver. Hypertension pathogenesis in male SHR instead manifested early as catecholaminergic gene expression changes in brainstem and kidney, followed by an upregulation of inflammation-related genes in liver. RAS-related gene expression from the kidney-liver-lung axis was downregulated and intra-adrenal RAS was upregulated in female SHR, whereas the opposite pattern of gene regulation was observed in male SHR. We identified disease-specific and sex-specific differences in regulatory interactions within and across organs. The inferred multi-organ network model suggests a diminished influence of central autonomic neural circuits over multi-organ gene expression changes in female SHR. Our results point to the gene regulatory influence of the adrenal gland on spleen in female SHR, as compared to brainstem influence on kidney in male SHR. Our integrated molecular profiling and network modeling identified a stage-specific, sex-dependent, multi-organ cascade of gene regulation during the development of hypertension.

A data-driven ISM-BN model for safety analysis of inland shipping in the Pearl River Basin

Inland shipping of the Pearl River plays an important role in the Chinese shipping system. To ensure navigation safety, we collect reports of maritime accidents from 2015 to 2022 in the Pearl River basin. This article extracts influencing factors by collecting the experience of inland waterway safety navigation and analyzing accident reports. Then, this paper uses the interpretative structural modeling method (ISM) to build a correlation model. Using a data-driven Bayesian network (BN), it analyzes the impact of various factors on the safety navigation in the Pearl River. The model validation is completed by compared with tree augmented naive Bayes classifiers (TAN) network using the same validation samples, through validation with the test set, the prediction accuracy has improved by 25%. The results indicate factors such as vessel type, accident month, accident day and time, etc. have a significant impact on the safety of navigation in the inland Pearl River waterway. The method used can identify important risk factors for accidents and the average predictive probability of validation samples reaches 87.03%. These research results could be extended to maritime management efforts in the Pearl River Basin.

Analysis and optimization of the efficient press shop operation

Abstract. In the last decade, stamping and forming manufacturing methods have been widely used in the manufacturing industry, and the stamping and forming industry has gradually shifted from the competition of scale and quantity to the competition of high quality, cost-effectiveness, and multi-category. Therefore, it is of far-reaching significance to study the efficient operation method of the press shop. In this paper, the efficient operation modeling method, digital simulation platform, and production line improvement of the press shop are reviewed. According to analysis, it can be concluded that the dynamic data-driven modeling method is perfect, but the theoretical basis involved in the practical application process is too complicated, therefore, press shop managers may be required to have a certain degree of theoretical basis so that the method can be effectively realized. Besides, the virtual-real combination of digital simulation platforms is easy to operate in the press shop, but the model assumptions analyzed in this paper are too idealized, and potential unresolved problems may arise in the practical application of the press shop with a larger scope and wider coverage. Finally, the production-based transformation of the shop floor production line is a more suitable management method for older factories that are ready for upgrading.

Advanced Monitoring and Real-Time State of Temperature Prediction in Lithium-Ion Cells Under Abusive Discharge Conditions Using Data-Driven Modelling

Advanced Monitoring and Real-Time State of Temperature Prediction in Lithium-Ion Cells Under Abusive Discharge Conditions Using Data-Driven Modelling

Enhancing data representation in forging processes: Investigating discretization and R-adaptivity strategies with Proper Orthogonal Decomposition reduction

Effective data reduction techniques are crucial for enhancing computational efficiency in complex industrial processes such as forging. In this study, we investigate various discretization and mesh adaptivity strategies using Proper Orthogonal Decomposition (POD) to optimize data reduction fidelity in forging simulations. We focus particularly on r-adaptivity techniques, which ensure a consistent number of elements throughout the field representation, filling a gap in existing research that predominantly concentrates on h-adaptivity. Our investigation compares isotropic mesh approaches with anisotropic mesh adaptations, including gradient-based, isolines-based, and spring-energy-based methods. Through numerical simulations and analysis, we demonstrate that these anisotropic techniques provide superior fidelity in representing deformation fields compared to isotropic meshes. These improvements are achieved while maintaining a similar level of model reduction efficiency. This enhancement in representation leads to improved data reduction quality, forming the foundation for data-driven models. This research contributes to advancing the understanding of mesh adaptivity approaches and their potential applications in data-driven modeling across various industrial domains.

Integrated Hybrid Modelling and Surrogate Model-Based Operation Optimization of Fluid Catalytic Cracking Process

Fluid Catalytic Cracking (FCC) is one of the most important conversion processes in oil refineries, widely used to convert high-boiling, high-molecular-weight hydrocarbon components from crude oil into more valuable products like gasoline and diesel. Advanced simulation and optimization technologies are critical for improving the operational efficiency and economic performance of the FCC process. First-principles-based simulators rely on parameter estimation and are computationally intensive, making them unsuitable for online optimization. In recent years, with the development of deep learning, data-driven models have made significant progress in FCC modeling. However, due to their black-box nature and difficulty with extrapolation, they are rarely used for optimization. To bridge this gap, we propose an integrated framework that combines hybrid modeling and surrogate model-based optimization. This approach combines plant and simulation data to train a multi-task learning prediction model, which then serves as a surrogate for operational optimization. Validated on a large-scale FCC unit in southern China, the model predicts product yields with an error margin of under 4.84% for all products. Following optimization, yields of LNG, gasoline, and diesel rose by an average of 0.10 wt%, 1.58 wt%, and 1.05 wt%, respectively, resulting in a 3.67% increase in product revenues. This highlights the substantial potential of this framework for industrial applications.

Data and model synergy-driven rolling bearings remaining useful life prediction approach based on deep neural network and Wiener process

Abstract Various Remaining Useful Life (RUL) prediction methods, encompassing model-based, data-driven, and hybrid methods, have been developed and successfully applied to prognostics and health management for diverse rolling bearing. Hybrid methods that integrate the advantages of model-based and data-driven approaches have garnered significant attention. However, the effective integration of the two methods to address the randomness in rolling bearing full lifecycle processes remains a significant challenge. To overcome the challenge, this paper proposes a data and model synergy-driven RUL prediction framework that includes two data and model synergy approaches. Firstly, a convolutional stacked bidirectional long and short-term memory network with temporal attention mechanism is established to construct health index. The RUL prediction is achieved based on HI and polynomial model. Secondly, a three-phase prediction model based on the Wiener process is established by considering the evolution law of different degradation phases. Then, two synergy methods are designed. Strategy 1: HI is adopted as the observation value for online updating of physics degradation model parameters under Bayesian framework, and the RUL prediction results are obtained from the physics degradation model. Strategy 2: The RUL prediction results from the data-driven and physics-based model are weighted linearly combined to improve the overall prediction accuracy. The effectiveness of the proposed model is verified using two bearing full lifecycle datasets. The results indicate that the proposed approach can accommodate both short-term and long-term RUL predictions, outperforming state-of-the-art single models.

Improving the potential of fifth-generation district heating and cooling networks through robust design and operational optimization under future energy market and demand uncertainties

Network investments and projected energy prices greatly impact the financial viability and environmental impact of fifth-generation district heating and cooling (5GDHC) networks. Compared to the previous generation, the upfront investment costs in 5GDHC networks are relatively high due to the decentralized energy demand and supply of the participating prosumers. The transition to 5GDHC is also hindered by uncertain energy markets and the fluctuating energy demands of the prosumers. It makes investors hesitant to commit, even for promising business cases. In this work, a framework is presented to assess the economic and environmental performance of a 5GDHC business case, based on a multi-objective robust optimization algorithm (MO-RDO), to identify the optimal trade-offs between environmental and economic designs. The proposed methodology consists of four steps. In the first two steps, a specific business case is modeled, and techno-economic and environmental performances are analyzed against uncertain energy markets. In the third step, the techno-economic and environmental indicator responses are used to develop a data-driven machine-learning model. This model offers better computational efficiency than a high-fidelity nonlinear model and assesses the most influential parameters driving economic and environmental performance via a global sensitivity analysis. This aids in refining the multi-objective robust design optimization (MO-RDO) framework by pinpointing key design variables and objectives amid data uncertainties. Additionally, the formulated MO-RDO provides a mix of environmentally and economically optimal network designs and operational parameters and highlights the trade-offs between them. The designs and trade-offs are evaluated using financial metrics like net present value (NPV), return on investment, and discounted payback period. These metrics are calculated over the project life, considering the initial investment and net savings. For the considered case, the environmental design has a 10% higher investment cost compared to the economically optimal solution but reduces total emissions (TE) by 13% and improves operational cost savings, which is crucial for better financial indicators. The proposed framework aligns with the EU transition plan to incorporate waste energy sources and decarbonization paths, estimating only a 3% increase in NPV as a risk for the environmentally optimal solution on a financial scale.

Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast

Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast

A refined grey Verhulst model for accurate degradation prognostication of PEM fuel cells based on inverse hyperbolic sine function transformation

Accurate prognostication of degradation plays an essential role in effectively enhancing the operational lifespan of proton exchange membrane fuel cells (PEMFCs). This paper proposes a novel enhanced correctional grey Verhulst model (IHS-CRGVM-RE), designed to prognosticate the degradation process of PEMFCs using the voltage of PEMFCs stack as a health indicator. First, the inverse hyperbolic sine function transformation is employed to attain optimal smoothness in data treatment. Then, the background value within the grey Verhulst model framework is modified based on cellular automata with rectangle techniques. Finally, a residual correction mechanism is applied to delineate the influences of error outcomes concerning PEMFCs degradation. Rigorous validation is provided via a comprehensive analysis based on two distinct PEMFCs datasets. The results demonstrate that the proposed model outperforms other data-driven models in prognostication accuracy, highlighting its significant importance for prognosticating the lifespan of PEMFCs.

Pioneering Museum Data Transformation: Unifying Legacy Systems and Enhancing Data Integrity

In the digital era, museums confront the challenge of modernising legacy data systems to align with current standards. Part of the RECODE (Rethinking Collections Data Ecosystems) Programme (Dupont et al. 2022) examines the complex transition from disparate departmental object models to a unified system, reflecting the broader museum community's struggle with data standardisation. The case study centres on consolidating five distinct data models accumulated over two decades, each tailored to different departmental needs under various constraints. The data mapping process identifies and aligns similar fields across models, facilitating the integration of analogous data points and exposing redundancies and unique practices embedded over years. Major challenges include data complexity, diversity, and quality issues (cleaning, standardizing, and deduplicating), compounded by the massive scale of the data: currently, the Natural History Museum London (NHM) has 262,831,590 records across 8,175 fields, and a total volume of 12 TB of data, which define both the ongoing data modelling work and our future data migration. A key innovation in our process is the immediate visibility of data issues that became apparent upon migrating to Amazon Web Services (AWS). AWS serves as the staging environment for our transition to the new NHM Collections Management System (CMS) and offers an unprecedented platform for directly addressing these challenges. It enables us to query all our data—across all departments and fields—in just seconds. This capability provides a comprehensive view that was previously unattainable. The core of this presentation is sharing "lessons learned" from navigating the intricacies of an ongoing CMS transition within a museum. The endeavor to untangle and unify diverse data models is a common challenge (IEEE Big Data Governance and Metadata Management Industry Connections Activity 2020,Wu et al. 2022, Wu et al. 2021,Little et al. 2022,Woodburn et al. 2022) highlighting the importance of community engagement and knowledge exchange. Our findings underscore the necessity of cross-departmental collaboration and the benefits of a data-driven data modelling approach. By sharing our journey and the developed comprehensive object model (Collier and Woodburn 2022), we aim to contribute valuable insights to museums undergoing similar transformations. The RECODE Programme sheds light on the practical aspects of CMS modernisation through the analytics and knowledge derived from over two decades of collections data and data use.