Two-dimensional Network Model Research Articles

Long-term forecasts of residential energy profiles based on Conv2D and LSTM models (electricity- and gas-based households)

For power system operation and expansion of grid-import systems, an accurate forecast model plays an essential role in the better management of household electricity demands. With the aim of finding an accurate forecast model in the proper representation of various household energy profiles, our research objective is centered on the development of a reliable forecast system for a group of 24-household energy consumers. In this energy study, we proposed long-term forecasts of (1) residential energy profiles within the multi-classification framework and (2) energy costing of the household demands using the Keras two-dimensional convolutional neural network (Conv2D) model and long short-term memory (LSTM) models. These high-level Keras neural networks are built to extract multivariate features for household energy consumption modeling and forecasting. The proposed forecast systems utilized a similar model hyperparameter configuration, while the forecast skills are validated with spatial–temporal variation datasets of ten remote locations. The actual costs of household demand and supply are estimated and compared with Conv2D predictions. The finding results (hourly and seasonal predictions and model evaluation) revealed that Conv2D and LSTM forecast systems are promising for household energy forecast solutions. Experimental results of the Conv2D predictive system achieved better forecast skills [correlation coefficient (0.727–0.994) and root mean square error (0.190–0.868)] than LSTM forecasts (0.308–0.987 and 0.278–1.212). However, experimental findings revealed that forecast skills of the predictive systems in residential energy demand predictions are highly influenced by the (1) quality of input datasets, (2) model hyperparameter tuning approach, and (3) learning rate of selected network optimizer(s).

Quantitative analysis of aflatoxin B1 in moldy peanuts based on near-infrared spectra with two-dimensional convolutional neural network

A two-dimensional convolutional neural network (2D-CNN) model based on Gramian angular summation field (GASF) image coding was proposed to detect aflatoxin B1 (AFB1) in moldy peanuts with high precision. Fourier transform near-infrared spectrometer was employed to acquire near-infrared spectra of moldy peanuts. The GASF was used to encode the NIR spectral features after principal component analysis. A convolutional neural network (CNN) framework was designed and the GASF-2D-CNN model was developed to realize the quantitative detection of AFB1 in peanuts. The results obtained showed that compared with the traditional chemometrics models and one-dimensional CNN (1D-CNN) model, the performance of GASF-2D-CNN model was significantly better than the previous two types of detection models. The root mean square error of prediction (RMSEP), coefficient of determination (RP2), relative percent deviation (RPD), and ratio of performance to interquartile range (RPIQ) of the best GASF-2D-CNN model were 2.0 μg·kg−1, 0.99, 8.3, and 9.3, respectively. The study reveals that GASF image coding technique can effectively mine the potential feature information in NIR spectra, and this technique will have a promising application prospect in the multivariable calibration of spectroscopy.

Transient prediction model of finned tube energy storage system based on thermal network

This paper proposed a two-dimensional thermal network model to predict the output of the finned tube energy storage system during the melting stage to solve the fast calculation of latent heat storage cooling equipment for high-energy airborne weapons. The thermal network model introduces effective thermal conductivity to consider the effect of natural convection on the melting of PCM. Numerical simulation and experiment verify the accuracy of a single tube under various working conditions and actual size heat exchangers, respectively. Compared with single-tube numerical simulation, the maximum average outlet temperature error is 0.634 °C, saving 99% of the simulation time. Compared with the experiment, the maximum temperature error of outlet temperature is 4.91%, and the average temperature error is 1.18%. Results are found to be in good agreement with numerical simulation and experiment. The performance of heat exchangers is evaluated by effectiveness under different conditions, including fin geometry, material, and periodic inlet. The results show that the structure with smaller fin thickness and interval has better effectiveness and latent heat storage, more benefits from increasing the fin thermal conductivity, and better stabilizes the outlet under the periodic inlet. It provides a reference for designing and optimizing energy storage systems.

Anomalous Hall conductivity and quantum friction

The anomalous Hall effect in high conductivity region is studied using a two-dimensional network model. We find that the off-diagonal conductivity comprises two parts: one which reflects the bulk properties as obtained by the Kubo formula and another which is sensitive to boundary conditions imposed on the network. In the fully coherent limit, the latter scales with the width of the conducting channel, while for real-world samples, it is controlled by the coherence length. It provides an alternative interpretation of the observed behavior in the clean limit which is otherwise attributed to the skew scattering. We highlight analogies to friction in viscous fluids responsible for Couette flow. In the present case, this quantum effect is governed by wave interference.

Computer-Aided Diagnosis for Tuberculosis Classification with Water Strider Optimization Algorithm

Computer-aided diagnosis (CAD) models exploit artificial intelligence (AI) for chest X-ray (CXR) examination to identify the presence of tuberculosis (TB) and can improve the feasibility and performance of CXR for TB screening and triage. At the same time, CXR interpretation is a time-consuming and subjective process. Furthermore, high resemblance among the radiological patterns of TB and other lung diseases can result in misdiagnosis. Therefore, computer-aided diagnosis (CAD) models using machine learning (ML) and deep learning (DL) can be designed for screening TB accurately. With this motivation, this article develops a Water Strider Optimization with Deep Transfer Learning Enabled Tuberculosis Classification (WSODTL-TBC) model on Chest X-rays (CXR). The presented WSODTL-TBC model aims to detect and classify TB on CXR images. Primarily, the WSODTL-TBC model undergoes image filtering techniques to discard the noise content and U-Net-based image segmentation. Besides, a pre-trained residual network with a two-dimensional convolutional neural network (2D-CNN) model is applied to extract feature vectors. In addition, the WSO algorithm with long short-term memory (LSTM) model was employed for identifying and classifying TB, where the WSO algorithm is applied as a hyperparameter optimizer of the LSTM methodology, showing the novelty of the work. The performance validation of the presented WSODTL-TBC model is carried out on the benchmark dataset, and the outcomes were investigated in many aspects. The experimental development pointed out the betterment of the WSODTL-TBC model over existing algorithms.

A short utterance speaker recognition method with improved cepstrum–CNN

In this study, an improved cepstrum-convolutional neural network is proposed, which can solve the problem of low recognition accuracy of 1-s short utterance in speaker recognition technology. The audio feature Mel frequency cepstrum coefficient is extracted by using the improved cepstrum algorithm and the data of the two-dimensional acoustic feature vector matrix is preprocessed to convert the two-dimensional feature matrix into a three-dimensional tensor as the input data of the two-dimensional convolutional neural network model. Experiments are carried out on an Arabic digital English pronunciation dataset with an audio duration of less than one second in a specific experimental environment. Moreover, the performance of this model is evaluated by accuracy and F1-score. The simulation results show that the accuracy of our proposed model for speech recognition is as high as 100% and 99.60% on the training and test sets, respectively, as well as the F1- score, is 0.9985. It can be seen that the recognition method of this model solves the problem of accuracy degradation of short utterance speaker recognition due to the short duration of the corpus and improves the accuracy of short speech voice recognition. The model is simple but effective, generalization, superior, and has higher practical application value.Article Highlights.It is interesting to study how to improve the accuracy of 1-s short utterance speaker recognition.The improved cepstrum algorithm can solve the problem of not extracting enough discernible acoustic features.This paper proposed model obtained 100% accuracy on a spoken Arabic digit dataset with an audio duration about 0.3 s.

Mixture 2D Convolutions for 3D Medical Image Segmentation.

Three-dimensional (3D) medical image segmentation plays a crucial role in medical care applications. Although various two-dimensional (2D) and 3D neural network models have been applied to 3D medical image segmentation and achieved impressive results, a trade-off remains between efficiency and accuracy. To address this issue, a novel mixture convolutional network (MixConvNet) is proposed, in which traditional 2D/3D convolutional blocks are replaced with novel MixConv blocks. In the MixConv block, 3D convolution is decomposed into a mixture of 2D convolutions from different views. Therefore, the MixConv block fully utilizes the advantages of 2D convolution and maintains the learning ability of 3D convolution. It acts as 3D convolutions and thus can process volumetric input directly and learn intra-slice features, which are absent in the traditional 2D convolutional block. By contrast, the proposed MixConv block only contains 2D convolutions; hence, it has significantly fewer trainable parameters and less computation budget than a block containing 3D convolutions. Furthermore, the proposed MixConvNet is pre-trained with small input patches and fine-tuned with large input patches to improve segmentation performance further. In experiments on the Decathlon Heart dataset and Sliver07 dataset, the proposed MixConvNet outperformed the state-of-the-art methods such as UNet3D, VNet, and nnUnet.

Detection of Malicious Network Flows with Low Preprocessing Overhead

Machine learning (ML) is frequently used to identify malicious traffic flows on a network. However, the requirement of complex preprocessing of network data to extract features or attributes of interest before applying the ML models restricts their use to offline analysis of previously captured network traffic to identify attacks that have already occurred. This paper applies machine learning analysis for network security with low preprocessing overhead. Raw network data are converted directly into bitmap files and processed through a Two-Dimensional Convolutional Neural Network (2D-CNN) model to identify malicious traffic. The model has high accuracy in detecting various malicious traffic flows, even zero-day attacks, based on testing with three open-source network traffic datasets. The overhead of preprocessing the network data before applying the 2D-CNN model is very low, making it suitable for on-the-fly network traffic analysis for malicious traffic flows.

Hierarchical Slice Patterns Inhibit Crack Propagation in Brittle Sheets

By introducing hierarchical patterns of load-parallel cuts into axially loaded brittle sheets, the resistance to propagation of mode-I cracks is very significantly enhanced. We demonstrate this effect by simulation of two-dimensional beam network models and experimentally by testing paper and polystyrene (PS) sheets that are sliced with a laser cutter to induce load-perpendicular hierarchical cut patterns. Samples endowed with nonhierarchical reference patterns of the same cut density and nonsliced sheets are considered for comparison. We demonstrate that hierarchical slicing can increase failure load, apparent fracture toughness, and work of fracture of notched paper and PS sheets by factors between 2 and 10.

Transferable Shape Estimation of Soft Pneumatic Actuators Based on Active Vibroacoustic Sensing

A soft pneumatic actuator (SPA) is one of the most prominent components in a soft robotic system. The sensing of SPAs is challenging owing to their elasticity and deformability. Sensors for specific factors are required to successfully sense an SPA. A flexible sensor is an important component for sensing the conditions of SPAs, such as the shape and deformation due to contact events during applications. Developing versatile sensors with high flexibility and tolerability for SPAs is challenging. Data-driven sensing approaches involve individual machine learning models for different actuators. In contrast, it is an enormous advantage to have versatile sensors as hardware and machine learning models as software employed on various actuators. Therefore, we propose a transferable shape estimation method based on active vibro-acoustic sensing to achieve tolerability and increase versatility. We created easily transferable sensing devices for SPAs. In addition, we employed a data-driven approach that utilizes a simple transfer learning technique on a two-dimensional convolutional neural network model. We confirm the feasibility and versatility of the proposed method through evaluation experiments. A transferable estimation method was used on SPAs to estimate the bending angle and length under various sensing and environmental conditions, and the average errors were less than 3.5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^\circ$</tex-math></inline-formula> and 2.1 mm, respectively.

Bolt-Loosening Detection Using 1D and 2D Input Data Based on Two-Stream Convolutional Neural Networks.

At present, the detection accuracy of bolt-loosening diagnoses is still not high. In order to improve the detection accuracy, this paper proposes a fault diagnosis model based on the TSCNN model, which can simultaneously extract fault features from vibration signals and time-frequency images and can precisely detect the bolt-loosening states. In this paper, the LeNet-5 network is improved by adjusting the size and number of the convolution kernels, introducing the dropout operation, and building a two-dimensional convolutional neural network (2DCNN) model. Combining the advantages of a one-dimensional convolutional neural network (1DCNN) with wide first-layer kernels to suppress high-frequency noise, a two-stream convolutional neural network (TSCNN) is proposed based on 1D and 2D input data. The proposed model uses raw vibration signals and time-frequency images as input and automatically extracts sensitive features and representative information. Finally, the effectiveness and superiority of the proposed approach are verified by practical experiments that are carried out on a machine tool guideway. The experimental results show that the proposed approach can effectively achieve end-to-end bolt-loosening fault diagnoses, with an average recognition accuracy of 99.58%. In addition, the method can easily achieve over 93% accuracy when the SNR is over 0 dB without any denoising preprocessing. The results show that the proposed approach not only achieves high classification accuracy but also has good noise immunity.

Prediction Model for Tea Polyphenol Content with Deep Features Extracted Using 1D and 2D Convolutional Neural Network

The content of tea polyphenols (TP) is one of the important indicators for judging the quality of tea. Accurate and non-destructive estimation technology for tea polyphenol content has attracted more and more attention, which has become a key technology for tea production, quality identification, grading and so on. Hyperspectral imaging technology is a fusion of spectral analysis and image processing technology, which has been proven to be an efficient technology for predicting tea polyphenol content. To make full use of spectral and spatial features, a prediction model of tea polyphenols based on spectral-spatial deep features extracted using convolutional neural network (CNN) was proposed, which not only broke the limitations of traditional shallow features, but also innovated the technical path of integrated deep learning in non-destructive detection for tea. Firstly, one-dimensional convolutional neural network (1D-CNN) and two-dimensional convolutional neural network (2D-CNN) models were constructed to extract the spectral deep features and spatial deep features of tea hyperspectral images, respectively. Secondly, spectral deep features, spatial deep features, and spectral-spatial deep features are used as input variables of machine learning models, including Partial Least Squares Regression (PLSR), Support Vector Regression (SVR) and Random Forest (RF). Finally, the training, testing and evaluation were realized using the self-built hyperspectral dataset of green tea from different grades and different manufacturers. The results showed that the model based on spectral-spatial deep features had the best prediction performance among the three machine learning models (R2 = 0.949, MAE = 0.533 for training sets, R2 = 0.938, MAE = 0.799 for test sets). Moreover, the visualization of estimation results of tea polyphenol content further demonstrated that the model proposed in this study had strong estimation ability. Therefore, the deep features extracted using CNN can provide new ideas for estimation of the main components of tea, which will provide technical support for the estimation tea quality estimation.

Modeling of three-phase radial flow reactor for diesel hydrotreating

• Mixing cell network model presented for industrial-scale three-phase Radial Flow Reactor for diesel hydrodesulfurization. • 2D MCN model was developed for Radial Flow Reactor (RFR) with one and five distributors to predict the product quality and bed temperature profiles. • Reactions like hydrodesulphurization (HDS), Hydrodearomatisation (HDA), and olefins saturation are taken into consideration. A mathematical model for a novel industrial-scale three-phase catalytic Radial Flow Reactor (RFR) has been developed using a two-dimensional mixing cell network (MCN) model. RFR is predominantly used for gaseous phase reactions in the petroleum refining industry. This work discusses the capabilities of three-phase RFR for diesel hydrodesulfurization. The reactions considered for the model development of diesel hydrodesulfurization are hydrodesulfurization, hydrodearomatisation, and olefins saturation. Apart from the well-known advantage of RFR, such as pressure drop, the analysis revealed other benefits such as better product quality, reduced H 2 S inhibition, no requirement of quench, high WABT. Simulations for RFR were performed for different gas distributors and results show that distributor design impacts the performance of reactor.

Utilizing a Two-Dimensional Data-Driven Convolutional Neural Network for Long-Term Prediction of Dissolved Oxygen Content

It is significant to establish a precise dissolved oxygen (DO) model to obtain clear knowledge ablout the prospective changing conditions of the aquatic environment of marine ranches and to ensure the healthy growth of fisheries. However Do in marine ranches is affected by many factors. DO trends have complex nonlinear characteristics. Therefore, the accurate prediction of DO is challenging. On this basis, a two-dimensional data-driven convolutional neural network model (2DD-CNN) is proposed. In order to reduce the influence of missing values on experimental results, a novel sequence score matching-filling (SSMF) algorithm is first presented based on similar historical series matching to provide missing values. This paper extends the DO expression dimension and constructs a method that can convert a DO sequence into two-dimensional images and is also convenient for the 2D convolution kernel to further extract various pieces of information. In addition, a self-attention mechanism is applied to construct a CNN to capture the interdependent features of time series. Finally, DO samples from multiple marine ranches are validated and compared with those predicted by other models. The experimental results show that the proposed model is a suitable and effective method for predicting DO in multiple marine ranches. The MSE MAE, RMSE and MAPE of the 2DD-CNN prediction results are reduced by 51.63, 30.06, 32.53, and 30.75% on average, respectively, compared with those of other models, and the R2 is 2.68% higher on average than those of the other models. It is clear that the proposed 2DD-CNN model achieves a high forecast accuracy and exhibits good generalizability.

Augmentation dataset of a two-dimensional neural network model for use in the car parts segmentation and car classification of three dimensions

Augmentation dataset of a two-dimensional neural network model for use in the car parts segmentation and car classification of three dimensions

Spectral technology and multispectral imaging for estimating the photosynthetic pigments and SPAD of the Chinese cabbage based on machine learning

• The estimation models constructed by spectra and multispectral imaging combined with various machine learning algorithms were compared. • A one-dimensional convolutional neural network model based on spectral data was established. • A two-dimensional convolutional neural network model based on multispectral images was established. • Spectra and multispectral images were combined with deep learning to achieve the estimation of multiple indicators, such as photosynthetic pigments and SPAD. The contents of photosynthetic pigment, which directly affect the growth of crops, could be evaluated with spectral and multispectral imaging technologies in an accurate and rapid way. For commodity germplasm resources on the market, the estimation of photosynthetic pigments and soil and plant analyzer development (SPAD) value was accomplished using the two techniques combined with machine learning. The spectrometer used in this study employed 781 bands from 320 nm to 1100 nm, and a multispectral imaging camera was used to acquire images in visible and near-infrared. Convolutional neural network (CNN), multiple linear regression (MLR) and generalized linear model (GLM) were used to establish the machine learning models, which established by preprocessed spectral data or 4-channel multispectral images. For estimating photosynthetic pigments (chlorophyll a , chlorophyll b , total chlorophyll and carotenoids), the GLM model established by spectral data was the optimal among all the models. For the SPAD optimal estimation model, the GLM model established by the spectral data and CNN model established by the multispectral images were fair. The R 2 and RMSE of the CNN model validation set in estimating SPAD were 0.87 and 2.31, respectively. The R 2 and RMSE of the GLM model validation set in estimating SPAD were 0.88 and 2.39, respectively. By combining two techniques with different machine learning methods, a comprehensive analysis of photosynthetic pigments and SPAD was accomplished in this paper.

Improvement and Validation of the System Analysis Model and Code for Heat-Pipe-Cooled Microreactor

Heat-pipe-cooled microreactors (HPMR) use a passive high-temperature alkali metal heat pipe to directly transfer the heat of solid core to the hot end of the intermediate heat exchanger or thermoelectric conversion device, thus avoiding a single point failure. To analyze and evaluate the transient safety characteristics of an HPMR system under accident conditions, such as heat pipe failure in the core or a loss of system heat sink and other accidents, a previously developed model for transient analysis of a heat-pipe-cooled space nuclear reactor power system (HPSR) was improved and validated in this study. The models improved mainly comprise: (1) An entire 2-D solid-core heat transfer model is established to analyze the accident conditions of core heat pipe failure and system heat sink loss. In this model, radial and axial Fourier heat conduction equations are used to divide the core into r-θ direction control volumes. The physical parameters of the material in the control volume are calculated according to the volume-weighted average. (2) By coupling the heat transfer limit model and the two-dimensional thermal resistance network model, the transient model of a heat pipe for HPMR system analysis is improved. (3) Conversion system models are established to simulate the system characteristics of the advanced HPMR concept, such as thermoelectric conversion, Stirling conversion, and the open Brayton conversion analysis model. Based on the improved models, the HPMR system analysis program TAPIRSD was developed, which was verified by experimental data of the separated conversion components and the ground nuclear test device KRUSTY. The maximum deviation of the power output predicted by the energy conversion model is less than 8%. The accident conditions of the KRUSTY tests, such as load change, core heat pipe failure, and heat sink loss accident, were studied by using TAPIRSD. The results show that the simulation results of the TAPIRSD code agree well with the experimental data of the KRUSTY prototype reactor. The maximum error between the TAPIRSD code prediction and the measured value of the core temperature under accident conditions is less than 10 K, and the maximum deviation is less than 2%. The results show that the developed code can predict the transient response process of the HPMR system well. At the same time, the accuracy and reliability of the improved model are proved. The TAPIRSD is suitable for system transient analysis of different types of HPMRs and provides an optional tool for the system safety characteristics analysis of HPMR.

Experimental Study of Water Displacement Rates on Remaining Oil Distribution and Oil Recovery in 2D Pore Network Model

An amount of oil remains in oil reservoirs even at the high water-cut stage of produced liquid from oil wells. To reveal the mechanism of displacement rates to affect the remaining oil in pore scales, a two-dimensional (2D) glass etching pore network model and real-time visual system were set up to observe the characteristics of oil distribution from water flooding and study the influence of displacement rates on oil recovery. It was found that the geometry of remaining oil in the pore network is diverse and dynamically changed at the high water-cut stage. Three geometric representative parameters were defined for the classification of five types of remaining oil (contiguous, branching, film, dropwise, bar columnar type), and controlling mechanisms for each type of remaining oil were analyzed. The experimental results show that the remaining oil saturation decreases from 21.2% to 6.5% when water injection rates increase from 0.05 to 0.5 mL/min. The increase in displacement rate improves the displacement efficiency of four types of remaining oil in the range of 55.00% to 93.67% except for dropwise type. The experimental data also indicate that the reduction in continuous residual oil and branched residual oil mainly contributes to the improvement of oil recovery of the whole network model. With the increase in displacement rate (from 0.05 to 0.1, 0.2, 0.3, 0.4, and 0.5 mL/min), the areas of five types of representative local residual oil reduce step by step. This research validates that the increase in water flooding rate in porous media leads to reduction in oil saturation, and it will improve oil recovery in oil reservoirs by enhancing water injection rates.

Fault Diagnosis of Planetary Gear Based on FRWT and 2D-CNN

The fault signals of planetary gears are nonstationary and nonlinear signals. It is difficult to extract weak fault features under strong background noise. This paper adopts a new filtering method, fractional Wavelet transform (FRWT). Compared with the traditional fractional Fourier transform (FRFT), it can improve the effect of noise reduction. This paper adopts a planetary gear fault diagnosis method combining fractional wavelet transform (FRWT) and two-dimensional convolutional neural network (2D-CNN). Firstly, several intrinsic mode component functions (IMFs) are obtained from the original vibration signal by AFSA-VMD decomposition, and the two components with the largest correlation coefficient are selected for signal reconstruction. Then, the reconstructed signal is filtered in fractional wavelet domain. By analyzing the wavelet energy entropy of the filtered signal, a two-dimensional normalized energy characteristic matrix is constructed and the two-dimensional features are input into the two-dimensional convolution neural network model for training. The simulation results show that the training effect of this method is better than that of FRFT-2D-CNN. Through the verification of the test set, we can know that the fault diagnosis of planetary gears can be realized accurately based on FRWT and 2D-CNN.

Connectivity, permeability and flow channelization in fractured karst reservoirs: A numerical investigation based on a two-dimensional discrete fracture-cave network model

Fractured karst reservoirs play a significant role in hydrocarbon reserves and groundwater storage. They often exhibit complex multiscale heterogeneities involving pores, fractures and caves, whose length scales range from microns to tens or hundreds of meters. Thus, the study of fractured karst reservoirs is faced with a significant unresolved challenge in quantitatively characterizing the geometrical connectivity and hydraulic conductivity as well as their interrelationships in such strongly heterogeneous, multicomponent systems. In this paper, we propose an analytical formulation to characterize the connectivity of discrete fracture-cave networks building upon the excluded area concept of the percolation theory. By implementing a state-of-the-art computational model solving coupled Navier-Stokes (free flow) and Darcy (porous media flow) equations, we numerically derive the permeability of a fractured and karstified porous media, such that the relationship between the connectivity and permeability is further explored. The high-fidelity numerical model also permits us to elucidate the process of flow channelization within the fracture-cave network. The results show that the fracture-cave network connectivity correlates to the permeability via a power law scaling for connected systems. Significant flow channeling occurs around the percolation threshold where the flow is dominated by a limited number of preferential pathways. Caves play a crucial role in the flow due to the fact that caves could globally enhance the network connectivity and locally serve as hotspots for high fluid velocity. Finally, a semi-analytical permeability model for fractured karst reservoirs is developed. The results of our research and insights obtained have important implications for understanding the subsurface fluid flow in fractured karst reservoirs.