Optimal Learning Method Research Articles

Aerodynamic robustness optimization of aeroengine fan performance based on an interpretable dynamic machine learning method

Aeroengines and gas turbines are susceptible to uncertainties during manufacturing and operation, leading to reduced efficiency and dispersed performance. Current engine design system often produces deterministic performance databases that cannot be effectively used to guide the uncertainty analysis and robust design process of turbomachinery. This paper proposes an interpretable dynamic machine learning method for sensitivity analysis and robust optimization of turbomachinery blades. A dynamic extreme gradient boosting (XGBoost) is trained to predict fan aerodynamic performance, and the SHapley additional explanation (SHAP) method is introduced to explain regression model behavior and identify the impact of uncertain variables. On this basis, the Lipschitz-based trust region (MAXLIPO-TR) optimization algorithm is used to obtain the optimal configuration with the best robustness performance. Finally, the method is applied to data mining for design guidelines of robustness performance enhancement of an aeroengine fan. The results show that maximum camber and tangential stacking have major effects on fan performance dispersion. The standard deviation of the isentropic efficiency, pressure ratio and mass flow rate of the optimized configuration are reduced by 42.4%, 35.6% and 22.7% respectively at design conditions. The proposed data mining method has scientific significance and industrial application value in the robust design of advanced turbomachinery.

Large Language Model and Digital Twins Empowered Asynchronous Federated Learning for Secure Data Sharing in Intelligent Labeling

With the advancement of the large language model (LLM), the demand for data labeling services has increased dramatically. Big models are inseparable from high-quality, specialized scene data, from training to deploying application iterations to landing generation. However, how to achieve intelligent labeling consistency and accuracy and improve labeling efficiency in distributed data middleware scenarios is the main difficulty in enhancing the quality of labeled data at present. In this paper, we proposed an asynchronous federated learning optimization method based on the combination of LLM and digital twin technology. By analysising and comparing and with other existing asynchronous federated learning algorithms, the experimental results show that our proposed method outperforms other algorithms in terms of performance, such as model accuracy and running time. The experimental validation results show that our proposed method has good performance compared with other algorithms in the process of intelligent labeling both in terms of accuracy and running solves the consistency and accuracy problems of intelligent labeling in a distributed data center.

Multi-criteria study and machine learning optimization of a novel heat integration for combined electricity, heat, and hydrogen production: Application of biogas-fueled S-Graz plant and biogas steam reforming

The current research introduces an environmentally friendly heat design method by employing biogas fuel, aiming to yield electricity, hydrogen, and heating load simultaneously. The proposed arrangement consists of a biogas-powered S-Graz plant and a biogas steam reforming cycle. Although methane-fueled S-Graz plants for multigeneration purposes have been studied in previous studies, research on employing biogas fuel to launch a S-Graz plant and integrating a biogas steam reforming cycle with such a plant has yet to be examined. The model is simulated using the engineering equation solver software, and the study includes thermodynamic, exergoeconomic, and sustainability assessments to show the potential of the suggested configuration. By conducting a sensitivity study, a machine learning optimization method within MATLAB is implemented to exhibit the final optimal solution for the proposed arrangement. This optimization uses artificial neural networks and a non-dominated sorting genetic algorithm-II algorithm in a triple-objective framework based on energy efficiency, sustainability index, and products’ specific cost. The optimization demonstrates that the mentioned objectives reach optimal values of 58.26 %, 4.56, and 15.56 $/GJ, respectively. Also, the optimal net output power and hydrogen production rate equal 5746 kW and 1.45 m3/s, respectively. Besides, the process determines the optimal exergy efficiency, total net present value, and payback period as 52.70 %, 50.3 M$, and 8.96 years, respectively. The total investment cost rate for this system also is found to be 219.8 $/h.

A one-time training machine learning method for general structural topology optimization

Machine learning (ML) methods have found some applications in structural topology optimization. In the existing methods, however, the ML models need to be retrained when the design domains and supporting conditions have been changed, posing a limitation to their wide applications. In this paper, we propose a one-time training ML (OTML) method for general topology optimization, where the self-attention convolutional long short-term memory (SaConvLSTM) model is introduced to update the design variables. An extension–division approach is used to enrich the training sets. By developing a splicing strategy, the training results of a small design space (i.e., a basic cell of either two- or three-dimensions) can be extended to tackling the optimization problem of a large design domain with arbitrary geometric shapes. Using the OTML method, the ML model needs to be trained for only one time, and the trained model can be used directly to solve various optimization problems with arbitrary shapes of design domains, loads, and boundary conditions. In the SaConvLSTM model, the material volume of the post-processed thresholded designs can be precisely controlled, though the control precision of the gray-scale designs might be slightly sacrificed. The effects of model parameters on the computational cost and the result quality are examined. Four examples are provided to demonstrate the high performance of this structural design method. For large-scale optimization problems, the present method can accelerate the structural form-finding process. This study holds a promise in the high-resolution structural form-finding and transdisciplinary computational morphogenesis.

Multi-scale fusion pixel and instance contrastive self-supervised learning for semantic segmentation of high-resolution Earth surface images

In the field of remote sensing (RS) image semantic segmentation, existing supervised learning methods rely on a large amount of labeled data, which limits their application scope. To solve this problem, we propose a new self-supervised learning method, called multi-scale fusion pixel and instance contrastive learning network (MPINet). This method first uses focal frequency loss to optimize the learning of high-level semantic information, and then strengthens the spatial information in the shallow feature map through multi-scale fusion pixel contrast learning, thereby improving the model’s ability to mine detailed features. Experiments are conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam, LoveDA and UAVid datasets. The results show that our method achieves 49.89%, 70.98% and 63.55% in mIoU, OA and mF1 indicators on the ISPRS Potsdam dataset, which is 1.48%, 1.71% and 0.95% higher than the best method. On the LoveDA dataset, our method achieves 38.05%, 52.89% and 54.10% in mIoU, OA and mF1 indicators, which is 0.6%, 0.91% and 1.04% higher than the best method. On the UAVid dataset, our method achieved mIoU, OA, and mF1 scores of 57.92%, 76.97%, and 73.28%, respectively, representing improvements of 1.06%, 1.46%, and 1.15% compared to the best method. Experimental results show that the proposed method outperforms the existing optimal self-supervised learning method and the ImageNet pre-training method.

SGRTmreg: A Learning-Based Optimization Framework for Multiple Pairwise Registrations.

Point cloud registration is a fundamental task in computer vision and graphics, which is widely used in 3D reconstruction, object tracking, and atlas reconstruction. Learning-based optimization and deep learning methods have been widely developed in pairwise registration due to their own distinctive advantages. Deep learning methods offer greater flexibility and enable registering unseen point clouds that are not trained. Learning-based optimization methods exhibit enhanced robustness and stability when handling registration under various perturbations, such as noise, outliers, and occlusions. To leverage the strengths of both approaches to achieve a less time-consuming, robust, and stable registration for multiple instances, we propose a novel computational framework called SGRTmreg for multiple pairwise registrations in this paper. The SGRTmreg framework utilizes three components-a Searching scheme, a learning-based optimization method called Graph-based Reweighted discriminative optimization (GRDO), and a Transfer module to achieve multi-instance point cloud registration.Given a collection of instances to be matched, a template as a target point cloud, and an instance as a source point cloud, the searching scheme selects one point cloud from the collection that closely resembles the source. GRDO then learns a sequence of regressors by aligning the source to the target, while the transfer module stores and applies the learned regressors to align the selected point cloud to the target and estimate the transformation of the selected point cloud. In short, SGRTmreg harnesses a shared sequence of regressors to register multiple point clouds to a target point cloud. We conduct extensive registration experiments on various datasets to evaluate the proposed framework. The experimental results demonstrate that SGRTmreg achieves multiple pairwise registrations with higher accuracy, robustness, and stability than the state-of-the-art deep learning and traditional registration methods.

A maximum entropy deep reinforcement learning method for sequential well placement optimization using multi-discrete action spaces

Well placement optimization is a crucial method to solve the planar conflicts in reservoir development, mainly to determine the optimal well locations and drilling sequence to maximize the economic benefits of reservoir development. However, the current well placement optimization methods face the problems of high-dimensional discretization of optimization variables and lack of effective incentives for policy exploration, which make it challenging to improve the global optimization ability (the ability to jump out of locally optimal solutions in time and continuously search for better solutions in the whole optimization process) and real-time adjustability of the well placement optimization methods under limited numerical simulation times. In this paper, we propose a new sequential well placement optimization method, based on the Discrete Soft Actor-Critic Algorithm (DSAC), which incorporates the maximum entropy mechanism to formulate well placement and drilling sequencing schemes more efficiently and maximize the net present value (NPV) over the entire life cycle of reservoir development. Specifically, the method models the well placement optimization problem as a Markov Decision Process (MDP) and achieves sequential well placement optimization by training a Deep Reinforcement Learning (DRL) agent that maps reservoir states to a stochastic policy of well placement variables as well as evaluates the value function of the current policy. The DRL agent can determine the optimal infill well location in real-time based on the reservoir state at different times during the development process, thus obtaining the optimal drilling sequence. The proposed method in this paper has two innovations. First, by reconstructing the large-scale discrete action space of well placement optimization variables into multi-discrete action spaces, and with the maximum entropy mechanism, policy exploration is encouraged to improve the global optimization capability. Second, the trained policy can swiftly adapt the subsequent well placement scheme for a specific state of the target reservoir without the requirement to initiate training from scratch, which can realize the offline application of the trained policy and has better real-time adjustability. To verify the effectiveness of the proposed method, it is tested in 2D and 3D reservoir models. The results show that DSAC not only outperforms the gradient-based optimization method, classical evolutionary algorithms, and existing reinforcement learning proximal policy optimization (PPO) method in terms of global optimization ability but also shows better real-time adjustability of the trained policy when applied offline.

Customer-to-customer returns logistics: Can it mitigate the negative impact of online returns?

Customer returns are a major problem for online retailers due to their economic and environmental impact. This paper investigates a new concept for handling online returns: customer-to-customer (C2C) returns logistics. The idea behind the C2C concept is to deliver returned items directly to the next customer, bypassing the retailer’s warehouse. To incentivize customers to purchase C2C return items, retailers can promote return items on their webshop with a discount. We build the mathematical models behind the C2C concept to determine how much discount to offer to ensure enough customers are induced to purchase C2C return items and to maximize the retailer’s expected total profit. Our first model, the base model (BM), is a customer-based formulation of the problem and provides an easy-to-implement constant-discount-level policy. Our second model formulates the real-world problem as a Markov decision process (MDP). Since our MDP suffers from the curse of dimensionality, we resort to simulation optimization (SO) and reinforcement learning (RL) methods to obtain reasonably good solutions. We apply our methods to data collected from a Dutch fashion retailer. We also provide extensive numerical experiments to claim generality. Our results indicate that the constant-discount-level policy obtained with the BM performs well in terms of expected profit compared to SO and RL. With the C2C concept, significant benefits can be achieved in terms of both expected profit and return rate. Even in cases where the cost-effectiveness of the C2C returns program is not pronounced, the proportion of customer-to-warehouse returns to total demand becomes lower. Therefore, the system can be defined as more environmentally friendly. The C2C concept can help retailers financially address the problem of online returns and meet the growing need for reducing their environmental impact.

Infrared small target detection algorithm based on filter kernel combination optimization learning method

Infrared small target detection in complex backgrounds remains a big challenge due to its small size and weak energy, which makes it easy to be submerged in complex backgrounds. Common filtering algorithms are difficult to apply to various complex scenes and generate many false alarms and poor robustness. Therefore, this paper proposes an infrared small target detection algorithm based on filter kernel combination optimization learning method. For the sample image block use typical filter kernels and weight coefficients to calculate the combination of filtering results, and construct the loss function of the results and the true value. The optimal weight coefficients are learned using an optimization method, which effectively achieves the fusion of multiple features, then we build a sample library containing comprehensive priori information. In the implementation, an online inference method based on similarity measure is proposed to match test images with sample library image blocks to obtain optimal combination weights. By utilizing the comprehensive priori information to enhance the adaptive ability of the algorithm for various complex backgrounds. Finally, get the position of the infrared small target. The experimental results show that our algorithm has excellent detection performance for infrared small targets with complex background and low signal to clutter ratio, and the AUC value is 0.9980, which is more robust than other comparative algorithms.

A novel feature optimization and ensemble learning method for state-of-health prediction of mining lithium-ion batteries

In this work, accelerated aging tests at different temperatures are conducted for 228Ah mining lithium-ion batteries, and an SOH prediction method with health features (HFs) optimization and ensemble learning method is proposed. Firstly, six health features are extracted from cyclic charge/discharge data. Simultaneously, to solve the problem of a single feature not fully reflecting the SOH at multiple temperatures, canonical correlation analysis is introduced to construct the feature fusion vector to obtain the comprehensive health feature (C–HF). Secondly, the complementary ensemble empirical mode decomposition method is used to smooth the features and the SOH of the battery to extract the raw data of the battery to be tested in the stable frequency range. Then, four different datasets are used to comprehensively evaluate the performance of C–HF in the ensemble learning method. Compared with other HFs, the optimized feature C–HF has the best SOH prediction in all datasets, with high prediction accuracy and strong robustness. Finally, we compare SVM, LSTM, and LSTM-SVM with the proposed method in this paper for SOH prediction. Whether 70 % or 30 % of training datasets are used, the proposed method's estimation results are closer to the actual in SOH.

Machine learning optimization strategy of shaped charge liner structure based on jet penetration efficiency

Shaped charge liner (SCL) has been extensively applied in oil recovery and defense industries. Achieving superior penetration capability through optimizing SCL structures presents a substantial challenge due to intricate rate-dependent processes involving detonation-driven liner collapse, high-speed jet stretching, and penetration. This study introduces an innovative optimization strategy for SCL structures that employs jet penetration efficiency as the primary objective function. The strategy combines experimentally validated finite element method with machine learning (FEM-ML). We propose a novel jet penetration efficiency index derived from enhanced cutoff velocity and shape characteristics of the jet via machine learning. This index effectively evaluates the jet penetration performance. Furthermore, a multi-model fusion based on a machine learning optimization method, called XGBOOST-MFO, is put forward to optimize SCL structure over a large input space. The strategy's feasibility is demonstrated through the optimization of copper SCL implemented via the FEM-ML strategy. Finally, this strategy is extended to optimize the structure of the recently emerging CrMnFeCoNi high-entropy alloy conical liners and hemispherical copper liners. Therefore, the strategy can provide helpful guidance for the engineering design of SCL.

Coupled mode theory for plasmonic couplers

Photonic integrated circuits play an increasingly important role in several emerging technologies. Their functionality arises from a combination of integrated components, e.g., couplers, splitters, polarization rotators, and wavelength selective filters. Efficient and accurate simulation of these components is crucial for circuit design and optimization. In dielectric systems, design procedures typically rely on coupled-mode theory (CMT) methods, which then guide subsequent refined full-wave calculations. Miniaturization to deep sub-wavelength scales requires the inclusion of lossy plasmonic (metal) components, making optimization more complicated by the interplay between coupling and absorption. Even though CMT is well developed, there is no consensus as to how to rigorously and quantitatively implement it for lossy systems. Here we present an intuitive coupled-mode theory framework for quantitative analysis of dielectric–plasmonic directional and adiabatic couplers, whose large-scale implementation in 3D is prohibitively slow with full-wave methods. This framework relies on adapting existing coupled mode theory approaches by including loss as a perturbation. This approach will be useful in designing dielectric–plasmonic circuits, providing a first reference point for anyone using techniques such as inverse design and deep learning optimization methods.

Optimizing System Resources and Adaptive Load Balancing Framework Leveraging ACO and Reinforcement Learning Algorithms

In today's constantly changing computer settings, the most important things for improving speed and keeping stability are making the best use of system resources and making sure that load balancing works well. To achieve flexible load balancing and resource optimization, this study suggests a new system that combines the Ant Colony Optimization (ACO) and Reinforcement Learning (RL) methods. The structure is meant to help with the problems that come up when tasks and resource needs change in big spread systems. ACO is based on how ants find food and is used to change how jobs are distributed among computer nodes based on local knowledge and scent tracks. This autonomous method makes it easy to quickly look for solutions and adjust to new situations. In addition to ACO, RL methods are used to learn about and adjust to how the system changes over time. By planning load balancing as a series of decisions, RL agents are able to keep improving their rules so that the system works better and resources are used more efficiently. Agents learn the best ways to divide up tasks and use resources by interacting with the world and getting feedback. The suggested system works in a spread way, which makes it scalable and reliable in a variety of settings. The system changes its behavior on the fly to react to changing tasks and resource availability by using the group intelligence of ACO and the flexibility of RL. The system can also handle different improvement goals and limitations, which makes it flexible and usable in a range of situations. The suggested approach works better than standard load balancing methods at improving system performance, lowering reaction times, and making the best use of resources, as shown by the results of experiments. Using the strengths of the ACO and RL algorithms, this structure looks like a good way to deal with the complexity of current computer systems and make good use of resources in changing settings

A method for intelligent identification of faults in seismic using an attention-based ES-UNet network with model re-training learning

Accurate fault identification provides an important basis for well location deployment, oil and gas resource development. However, obtaining a large number of fault samples through manual labeling or interpretation is difficult. Conventional convolutional neural networks have certain challenges in finely characterizing low-order faults and fault continuity. This paper studies a 3D intelligent fault identification method that integrates deep learning with attention mechanism. Based on 3D-UNet network, the method constructs a dual attention fault identification model with an encoder-decoder structure, which focuses on enhancing low-order fault information and extracting key features. An adaptive hybrid loss function is proposed to address the imbalance problem of fault proportions in seismic amplitude data. The function introduces an adjustment coefficient to adaptively enhance the attention to high-order or low-order faults according to the actual situation of the fault, improving the accuracy and continuity of fault identification. Furthermore, a model re-training learning optimization method is presented to capture the missed fault information in the first training and repair the connectivity of low-order faults. Applying this method to the synthetic data set, the accuracy can be improved to 0.9732, and the loss can be converged to 0.0982. The results of shale reservoirs in the North Sea Basin and Kerry-3D indicate that the method can reduce the situation of fault missing and misidentification, effectively improve fault identification accuracy, and enhance low-order fault identification by obtaining more contextual fault features.

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Accurate instantaneous electricity peak load prediction is crucial for efficient capacity planning and cost-effective electricity network establishment. This paper aims to enhance the accuracy of instantaneous peak load forecasting by employing models incorporating various optimization and machine learning (ML) methods. This study examines the impact of independent inputs on peak load estimation through various combinations and subsets using multilinear regression (MLR) equations. This research utilizes input data from 1980 to 2020, including import and export data, population, and gross domestic product (GDP), to forecast the instantaneous electricity peak load as the output value. The effectiveness of these techniques is evaluated based on error metrics, including mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R2. The comparison extends to popular optimization methods, such as particle swarm optimization (PSO), and the newest method in the field, including dandelion optimizer (DO) and gold rush optimizer (GRO). This comparison is made against conventional machine learning methods, such as support vector regression (SVR) and artificial neural network (ANN), in terms of their prediction accuracy. The findings indicate that the ANN and GRO approaches produce the least statistical errors. Furthermore, the correlation matrix indicates a robust positive linear correlation between GDP and instantaneous peak load. The proposed model demonstrates strong predictive capabilities for estimating peak load, with ANN and GRO performing exceptionally well compared to other methods.

Hybrid approaches to optimization and machine learning methods: a systematic literature review

Notably, real problems are increasingly complex and require sophisticated models and algorithms capable of quickly dealing with large data sets and finding optimal solutions. However, there is no perfect method or algorithm; all of them have some limitations that can be mitigated or eliminated by combining the skills of different methodologies. In this way, it is expected to develop hybrid algorithms that can take advantage of the potential and particularities of each method (optimization and machine learning) to integrate methodologies and make them more efficient. This paper presents an extensive systematic and bibliometric literature review on hybrid methods involving optimization and machine learning techniques for clustering and classification. It aims to identify the potential of methods and algorithms to overcome the difficulties of one or both methodologies when combined. After the description of optimization and machine learning methods, a numerical overview of the works published since 1970 is presented. Moreover, an in-depth state-of-art review over the last three years is presented. Furthermore, a SWOT analysis of the ten most cited algorithms of the collected database is performed, investigating the strengths and weaknesses of the pure algorithms and detaching the opportunities and threats that have been explored with hybrid methods. Thus, with this investigation, it was possible to highlight the most notable works and discoveries involving hybrid methods in terms of clustering and classification and also point out the difficulties of the pure methods and algorithms that can be strengthened through the inspirations of other methodologies; they are hybrid methods.

Artificial intelligence in healthcare: combining deep learning and Bayesian optimization to forecast COVID-19 confirmed cases.

Healthcare is a topic of significant concern within the academic and business sectors. The COVID-19 pandemic has had a considerable effect on the health of people worldwide. The rapid increase in cases adversely affects a nation's economy, public health, and residents' social and personal well-being. Improving the precision of COVID-19 infection forecasts can aid in making informed decisions regarding interventions, given the pandemic's harmful impact on numerous aspects of human life, such as health and the economy. This study aims to predict the number of confirmed COVID-19 cases in Saudi Arabia using Bayesian optimization (BOA) and deep learning (DL) methods. Two methods were assessed for their efficacy in predicting the occurrence of positive cases of COVID-19. The research employed data from confirmed COVID-19 cases in Saudi Arabia (SA), the United Kingdom (UK), and Tunisia (TU) from 2020 to 2021. The findings from the BOA model indicate that accurately predicting the number of COVID-19 positive cases is difficult due to the BOA projections needing to align with the assumptions. Thus, a DL approach was utilized to enhance the precision of COVID-19 positive case prediction in South Africa. The DQN model performed better than the BOA model when assessing RMSE and MAPE values. The model operates on a local server infrastructure, where the trained policy is transmitted solely to DQN. DQN formulated a reward function to amplify the efficiency of the DQN algorithm. By examining the rate of change and duration of sleep in the test data, this function can enhance the DQN model's training. Based on simulation findings, it can decrease the DQN work cycle by roughly 28% and diminish data overhead by more than 50% on average.

An Improved Bayesian Learning Method for Distribution Grid Fault Location and Meter Deployment Optimization

An Improved Bayesian Learning Method for Distribution Grid Fault Location and Meter Deployment Optimization

Adaptive Individual Q-Learning—A Multiagent Reinforcement Learning Method for Coordination Optimization

Adaptive Individual Q-Learning—A Multiagent Reinforcement Learning Method for Coordination Optimization

Multimodal Feature Fusion Using Optimal Transfer Learning Approach for Lung Cancer Detection and Classification on CT Images

Lung cancer detection is the process of detecting the presence of lung tumor or abnormalities in the lungs. Early diagnosis is crucial for increasing the chances of patient survival and successful treatment. When compared to X-rays, Computed Tomography (CT) images are more sensitive and are increasingly being used for the diagnosis and screening of lung tumors. They provide complete cross-sectional images of the lungs and it will even detect small lesions. AI and Machine learning (ML) approaches are most commonly employed to analyse medical images (e.g. CT scans) and detect lung cancer. This algorithm can help radiologists identify patterns indicative or subtle abnormalities of cancer. Medical diagnosis, particularly in complex diseases such as lung cancer, frequently involves ambiguity. The diagnostic system can alleviate ambiguity via cross-verifying findings from various sources by fusing multimodal features. Multimodal feature fusion using deep learning (DL) algorithm is an advanced technology that leverages the abilities of deep neural networks to combine data from three different modalities or sources for better robustness in several applications, namely natural language processing, image, and data analysis, etc. This study introduces a Multimodal Feature Fusion using an Optimal Transfer Learning Method for Lung Cancer Detection and Classification (MFFOTL-LCDC) methodology on CT images. The chief objective of the MFFOTL-LCDC methodology is to exploit the feature fusion process for the identification and classification of lung tumor. To attain this, the MFFOTL-LCDC model undergoes a multimodal feature fusion approach to derive feature vectors using 3 DL approaches such as SqueezeNet, CapsNet, and Inception v3 models. Besides, the MFFOTL-LCDC technique applies the remora optimization algorithm (ROA) for the hyperparameter choice of 3 DL models. For lung cancer recognition, the MFFOTL-LCDC algorithm exploits the deep extreme learning machine (DELM) algorithm. A series of simulations were conducted to ensure the greater lung cancer recognition outcomes of the MFFOTL-LCDC methodology. The extensive outcomes determine the improved results of the MFFOTL-LCDC technique over recent DL approaches.