One-dimensional Convolutional Neural Network Research Articles

Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition.

Gesture recognition using electromyography (EMG) signals has prevailed recently in the field of human-computer interactions for controlling intelligent prosthetics. Currently, machine learning and deep learning are the two most commonly employed methods for classifying hand gestures. Despite traditional machine learning methods already achieving impressive performance, it is still a huge amount of work to carry out feature extraction manually. The existing deep learning methods utilize complex neural network architectures to achieve higher accuracy, which will suffer from overfitting, insufficient adaptability, and low recognition accuracy. To improve the existing phenomenon, a novel lightweight model named dual stream LSTM feature fusion classifier is proposed based on the concatenation of five time-domain features of EMG signals and raw data, which are both processed with one-dimensional convolutional neural networks and LSTM layers to carry out the classification. The proposed method can effectively capture global features of EMG signals using a simple architecture, which means less computational cost. An experiment is conducted on a public DB1 dataset with 52 gestures, and each of the 27 subjects repeats every gesture 10 times. The accuracy rate achieved by the model is 89.66%, which is comparable to that achieved by more complex deep learning neural networks, and the inference time for each gesture is 87.6 ms, which can also be implied in a real-time control system. The proposed model is validated using a subject-wise experiment on 10 out of the 40 subjects in the DB2 dataset, achieving a mean accuracy of 91.74%. This is illustrated by its ability to fuse time-domain features and raw data to extract more effective information from the sEMG signal and select an appropriate, efficient, lightweight network to enhance the recognition results.

Fault detection and isolation of floating wind turbine pitch system based on Kalman filter and multi-attention 1DCNN

In this paper, the fault detection and isolate problem is investigated for the pitch system of floating wind turbine. In the addressed system model, the system noises and measurement noises are correlated, and the measurement is affected by the missing phenomena. A Kalman filter is designed to handle the correlated noises and estimate the pitch angle, and a residual of the measurement of the pitch system is constructed to detection the faults. Then the fault isolation algorithm is presented based on a multi-attention mechanism one-dimensional convolutional neural network, which is employed to accurately isolate the faults. The simulation results show that the proposed method can significantly improve the accuracy of fault detection and isolation, which the fault isolation accuracy of the simulation results reaches 99.15%.

Structural Condition Assessment of Steel Anchorage Using Convolutional Neural Networks and Admittance Response

Structural damage in the steel bridge anchorage, if not diagnosed early, could pose a severe risk of structural collapse. Previous studies have mainly focused on diagnosing prestress loss as a specific type of damage. This study is among the first for the automated identification of multiple types of anchorage damage, including strand damage and bearing plate damage, using deep learning combined with the EMA (electromechanical admittance) technique. The proposed approach employs the 1D CNN (one-dimensional convolutional neural network) algorithm to autonomously learn optimal features from the raw EMA data without complex transformations. The proposed approach is validated using the raw EMA response of a steel bridge anchorage specimen, which contains substantial nonlinearities in damage characteristics. A K-fold cross-validation approach is used to secure a rigorous performance evaluation and generalization across different scenarios. The method demonstrates superior performance compared to established 1D CNN models in assessing multiple damage types in the anchorage specimen, offering a potential alternative paradigm for data-driven damage identification in steel bridge anchorages.

Nondestructive detection and classification of impurities-containing seed cotton based on hyperspectral imaging and one-dimensional convolutional neural network

The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles, and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles. By fusing band combination optimization with deep learning, this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line. By applying hyperspectral imaging and a one-dimensional deep learning algorithm, we detect and classify impurities in seed cotton after harvest. The main categories detected include pure cotton, conveyor belt, film covering seed cotton, and film adhered to the conveyor belt. The proposed method achieves an impurity detection rate of 99.698%. To further ensure the feasibility and practical application potential of this strategy, we compare our results against existing mainstream methods. In addition, the model shows excellent recognition performance on pseudo-color images of real samples. With a processing time of 11.764 μs per pixel from experimental data, it shows a much improved speed requirement while maintaining the accuracy of real production lines. This strategy provides an accurate and efficient method for removing impurities during cotton processing.

Research on meat adulteration based on one-dimensional convolutional neural network (1DCNN) combined with electrochemical technology

Research on meat adulteration based on one-dimensional convolutional neural network (1DCNN) combined with electrochemical technology

Bending induced polarization charges in non-polar porous polymer for stroke rehabilitation

Owing to the flexibility, lightweight, long-life and low cost, polymers are promising candidates to realize electromechanical conversion in wearable electronics. The flexoelectric effect enables non-piezoelectric materials to achieve electromechanical coupling, thereby broadening application ranges of nonpolar polymers. In this work, the porous samples of polydimethylsiloxane (PDMS) with various pore sizes and porosities are fabricated by the sacrificial salt template method and the chemical gas foaming method. The flexoelectric polarization response can be tuned directly by the structural characters of the porous PDMS. The transverse flexoelectric coefficient of porous PDMS can reach approximately 2.9 times the counterpart of the bulk one. The competitive mechanism between strain gradient and permittivity is proposed on flexoelectricity of random porous media by dielectric impedance spectrums and finite element analyses. The present regulation of flexoelectricity provides an alternative to electromechanical conversion. With the deep learning technique based on one-dimensional convolution neural networks, actions of both sick and normal legs of various stroke patients can be well recognized by the designed device of rehabilitation. The present rehabilitation monitoring system, which is an innovative application of the flexoelectricity in the porous polymers, offers a new approach to support physical therapy for post-stroke patients.

Analyzing the opening and closing of windows in residential for predicting the energy consumption using optimized multi-scale convolution networks

PurposeThis proposal aims to forecast energy consumption in residential buildings based on the effect of opening and closing windows by the deep architecture approach. In this task, the developed model has three stages: (1) collection of data, (2) feature extraction and (3) prediction. Initially, the data for the closing and opening frequency of the window are taken from the manually collected datasets. After that, the weighted feature extraction is performed in the collected data. The attained weighted feature is fed to predict energy consumption. The prediction uses the efficient hybrid multi-scale convolution networks (EHMSCN), where two deep structured architectures like a deep temporal context network and one-dimensional deep convolutional neural network. Here, the parameter optimization takes place with the hybrid algorithm named jumping rate-based grasshopper lemur optimization (JR-GLO). The core aim of this energy consumption model is to predict the consumption of energy accurately based on the effect of opening and closing windows. Therefore, the offered energy consumption prediction approach is analyzed over various measures and attains an accurate performance rate than the conventional techniques.Design/methodology/approachAn EHMSCN-aided energy consumption prediction model is developed to forecast the amount of energy usage during the opening and closing of windows accurately. The emission of CO2 in indoor spaces is highly reduced.FindingsThe MASE measure of the proposed model was 52.55, 43.83, 42.01 and 36.81% higher than ANN, CNN, DTCN and 1DCNN.Originality/valueThe findings of the suggested model in residences were attained high-quality measures with high accuracy, precision and variance.

An explainable dual-mode convolutional neural network for multivariate time series classification

Multivariate time series classification (MTSC) is a crucial machine learning problem prevalent across various real-life domains. Traditional deep learning approaches with high accuracy in MTSC are often criticized for their “black box” nature, offering no insight into their operational mechanisms or decision-making processes. Explainable artificial intelligence (XAI) becomes a key idea for dealing with such limitations in decision-sensitive areas. While some researchers have explored the interpretability of MTSC, the majority have focused on elucidating the relationship between variables over time, neglecting the intricate connections among different variables. To address the interpretability issue in MTSC, we introduce an explainable dual-mode convolutional neural network (XDM-CNN) designed specifically for MTSC. The proposed XDM-CNN framework comprises two modules: a classification module and an explanation module. The classification module can ensure exceptional classification performance by combining both one-dimensional and two-dimensional convolutional neural networks, while the explanation module can mine the underlying logical relationships among variables during the classification process by utilizing a synergy of visualization and quantification techniques. We validate our approach using 26 datasets sourced from the University of East Anglia (UEA) archive. The experimental results demonstrate that XDM-CNN not only exhibits excellent performance in classification accuracy, but also has strong explainability. By combining visual and numerical explanation, the hidden logical relationships among multivariate time series are explored and interpreted, providing human users with a decidable basis for classification decisions.

Optical routing: link failure detection-aided optimal routing in elastic optical networks using hybrid deep learning with target-based feature pool formation

ABSTRACT The Elastic Optical Network (EON) is a kind of optical network where a large amount of data signals are given into the channel of optical fibre by modulating with the optical signal. One of the most crucial tasks for optical networks is resource allocation and routing, which has a significant impact on resource effectiveness and network capacity. Deep learning-based routing and resource allocation have piqued the interest of researchers to a considerable extent. Thus, this paper aims to develop efficient link failure detection in EONs with hybrid deep learning strategies. Initially, the data aggregation is performed to combine the multiple link information from EONs. The aggregated link data is given into the hybrid detection model named as Enhanced Deep Learning Network (EDLNet), where the One-Dimensional Convolutional Neural Network (1D-CNN) is used for extracting the features and used for generating the target-based feature pool. This feature pool is utilised in the Long Short-Term Memory (LSTM) network for detecting link failures. The parameter optimization is done by the hybrid 1DCNN-LSTM network with the support of the Hybrid Red Deer with Sewing Training-based Optimisation (HRD-STO) to achieve accurate detection results. The detected failed link is mitigated at the time of routing, and only reliable links are used to attain certain objective constraints. These objective constraints include shortest path, link reliability and stability, throughput and delay for enhancing the efficiency of the EONs. The replication analysis reveals the effectiveness of the proposed link failure detection model by comparing it with the conventional models.

Identification of hypermucoviscous Klebsiella pneumoniae K1, K2, K54 and K57 capsular serotypes by Raman spectroscopy

Antimicrobial resistance poses a significant challenge in modern medicine, affecting public health. Klebsiella pneumoniae infections compound this issue due to their broad range of infections and the emergence of multiple antibiotic resistance mechanisms. Efficient detection of its capsular serotypes is crucial for immediate patient treatment, epidemiological tracking and outbreak containment. Current methods have limitations that can delay interventions and increase the risk of morbidity and mortality. Raman spectroscopy is a promising alternative to identify capsular serotypes in hypermucoviscous K. pneumoniae isolates. It provides rapid and in situ measurements with minimal sample preparation. Moreover, its combination with machine learning tools demonstrates high accuracy and reproducibility. This study analyzed the viability of combining Raman spectroscopy with one-dimensional convolutional neural networks (1-D CNN) to classify four capsular serotypes of hypermucoviscous K. pneumoniae: K1, K2, K54 and K57. Our approach involved identifying the most relevant Raman features for classification to prevent overfitting in the training models. Simplifying the dataset to essential information maintains accuracy and reduces computational costs and training time. Capsular serotypes were classified with 96 % accuracy using less than 30 Raman features out of 2400 contained in each spectrum. To validate our methodology, we expanded the dataset to include both hypermucoviscous and non-mucoid isolates and distinguished between them. This resulted in an accuracy rate of 94 %. The results obtained have significant potential for practical healthcare applications, especially for enabling the prompt prescription of the appropriate antibiotic treatment against infections.

Blind source separation algorithm for noisy hydroacoustic signals based on decoupled convolutional neural networks

Wireless communication technology has been widely used in marine engineering, marine ranching and Marine environmental monitoring. However, structural redundancy and functional confusion exist in applying neural networks in signal separation technology in underwater communication environments, which can result in a slower rate of signal separation and lead to confusion of parameters during transfer learning. Based on this, an end-to-end, internal functionally structured decoupled neural network (D-CNN) blind source separation (BSS) model is proposed in this paper, which can realize a neural network BSS algorithm with a well-defined structure and function. The one-dimensional convolutional neural network layer is used in algorithm to automatically extract observed signal's features, based on the features, and there are two generation modules of separation matrix and scaling coefficients. Then the two modules can be used to separate the observed signal and adjust the signal coefficients to obtain the separated signal. Finally the transfer learning technique is used to generalize the model, which reduces the transfer cost of the model in different application scenarios. Experimental results show that when the communication distance is set to 0.02 km–2 km, the MSE of independent signal and related signal can be reduced by 14.24% and 14.95% respectively compared with the nearest Neural FCA algorithm. The results prove that the proposed algorithm can accurately estimate the source signal and improve the signal reception quality.

Abnormal Detection and Fault Diagnosis of Adjustment Hydraulic Servomotor Based on Genetic Algorithm to Optimize Support Vector Data Description with Negative Samples and One-Dimensional Convolutional Neural Network

Because of the difficulty in fault detection for and diagnosing the adjustment hydraulic servomotor, this paper uses feature extraction technology to extract the time domain and frequency domain features of the pressure signal of the adjustment hydraulic servomotor and splice the features of multiple pressure signals through the Multi-source Information Fusion (MSIF) method. The comprehensive expression of device status information is obtained. After that, this paper proposes a fault detection Algorithm GA-SVDD-neg, which uses Genetic Algorithm (GA) to optimize Support Vector Data Description with negative examples (SVDD-neg). Through joint optimization with the Mutual Information (MI) feature selection algorithm, the features that are most sensitive to the state deterioration of the adjustment hydraulic servomotor are selected. Experiments show that the MI algorithm has a better performance than other feature dimensionality reduction algorithms in the field of the abnormal detection of adjustment hydraulic servomotors, and the GA-SVDD-neg algorithm has a stronger robustness and generality than other anomaly detection algorithms. In addition, to make full use of the advantages of deep learning in automatic feature extraction and classification, this paper realizes the fault diagnosis of the adjustment hydraulic servomotor based on 1D Convolutional Neural Network (1DCNN). The experimental results show that this algorithm has the same superior performance as the traditional algorithm in feature extraction and can accurately diagnose the known faults of the adjustment hydraulic servomotor. This research is of great significance for the intelligent transformation of adjustment hydraulic servomotors and can also provide a reference for the fault warning and diagnosis of the Electro-Hydraulic (EH) system of the same type of steam turbine.

Multi-Perception Graph Convolution Transfer Network Bearing Fault Diagnosis Method

Targeting the challenge of variable working conditions in bearing fault diagnosis, most of the fault diagnosis methods based on transfer learning focus on the transfer of knowledge, resulting in a poor diagnosis effect in the target domain. To solve the problem of transfer performance degradation, a multi-perception graph convolution transfer network (MPGCTN) is proposed. The MPGCTN is composed of a graph generation module, graph perception module, and domain discrimination module. In the graph generation module, a one-dimensional convolution neural network (1-D CNN) is used to extract features from the input, and then the structural features of samples are mined in the graph generation layer to construct the sample graph. In the following graph perception module, a multi-perception graph convolution network is designed to model the sample graph and learn the data structure information of the sample. Finally, in the domain discrimination module, the method is used to align the structural differences of the case graphs in different domains. Experimental results from experiments on Case Western Reserve University (CWRU) and Paderborn University (PU) bearing datasets show that the proposed method is effective and superior.

Machine learning can predict implantable cardioverter defibrillator therapy: a development study

Abstract Introduction Remote monitoring (RM) data has been used to develop predictive algorithms that warn of decompensated heart failure before a heart failure episode. The same RM data could also be used to predict other adverse events in heart failure patients, such as ventricular arrhythmias. Machine learning (ML) models can be used to process complex multivariate time series RM data. Purpose The aim of this analysis was to generate a clinically useful model to predict defibrillator therapy (shock or anti-tachycardia pacing (ATP)). The output of the model is the likelihood of a shock in the next 24 hours. Methods RM data of all 292 implantable cardioverter defibrillators (ICDs) at our centre were collected (male 81%, 66±12 years). Electrograms of ICD therapies were manually verified. 63 time series variables were collated. Atrial lead-dependent RM parameters and ones with >30% missing data were excluded leaving 23 variables for analysis. After the exclusion of inappropriate therapies and patients with missing RM data, 218 patients were analysed. Of these, 41 (18.8%) had at least one ICD therapy. Three types of ML models were generated (1) random forest (RF), (2) extreme gradient boosted model (XGBoost), (3) one-dimensional convolutional neural network (1D-CNN) with three different intervals preceding ICD therapy: 30, 10, and 4 days. The model accuracy was measured utilising stratified grouped 5-fold cross-validation, with 20% of data used for testing in each fold. Results 4-day decision tree-based models (RF, XGBoost) demonstrated higher area under the curve (AUC) scores, compared with 10- and 30-day models. Percentage accuracy was similar across all three models and interval lengths. RF: The 4-day model had the highest AUC of 0.86 and an accuracy of 83.8%, compared to the 10-day (AUC 0.85, 83.0%) and 30-day (AUC 0.80, 82.2%) models. XGBoost: The 4-day model had an AUC of 0.85 and an accuracy of 83.4%, compared to the 10-day (AUC 0.84, 83.1%) and 30-day (AUC 0.81, 82.4%) models. 1D-CNN: The 4-day model had an AUC of 0.78 and an accuracy of 83.5%, compared to the 10-day (AUC 0.74, 83.1%) and 30-day (AUC 0.71, 82.2%) models. Episodes of prior ventricular tachycardia (VT) in the VT2 zone and prior ICD therapies contributed the most to model predictions, with their importance highest in the days immediately preceding ICD therapy (Figure 1). To better identify ‘first ICD therapy’, prior ICD therapies were excluded, and the models were re-run. AUC was lower at 0.70 with an accuracy of 72.9% in the highest-performing model (10-day XGBoost). The most important features were patient activity, RV pacing impedance, and mean ventricular heart rate (Figure 2). Conclusion We were able to predict ICD therapy with an AUC of 0.86. 4-day models were better than the 10-day and 30-day models. Model performance remained high (AUC 0.70), even after exclusion of prior ventricular arrhythmias from the predictors.1.Importance of top variables over time2.Top features without prior ICD therapy

Detection Method of Epileptic Seizures Using a Neural Network Model Based on Multimodal Dual-Stream Networks.

Epilepsy is a common neurological disorder, and its diagnosis mainly relies on the analysis of electroencephalogram (EEG) signals. However, the raw EEG signals contain limited recognizable features, and in order to increase the recognizable features in the input of the network, the differential features of the signals, the amplitude spectrum and the phase spectrum in the frequency domain are extracted to form a two-dimensional feature vector. In order to solve the problem of recognizing multimodal features, a neural network model based on a multimodal dual-stream network is proposed, which uses a mixture of one-dimensional convolution, two-dimensional convolution and LSTM neural networks to extract the spatial features of the EEG two-dimensional vectors and the temporal features of the signals, respectively, and combines the advantages of the two networks, using the hybrid neural network to extract both the temporal and spatial features of the signals at the same time. In addition, a channel attention module was used to focus the model on features related to seizures. Finally, multiple sets of experiments were conducted on the Bonn and New Delhi data sets, and the highest accuracy rates of 99.69% and 97.5% were obtained on the test set, respectively, verifying the superiority of the proposed model in the task of epileptic seizure detection.

Comparative analysis of classical artificial intelligence and deep learning models for atrial fibrillation detection in electrocardiograms

Abstract Background/Introduction Early diagnosis of atrial fibrillation (AF) presents a challenging yet critical task for appropriate interventions aimed at reducing disease-related burden. In this context, strategies employing classical artificial intelligence (CAI) and deep learning (DL) have emerged as promising approaches to optimize cardiac disorder screening and detection. Purpose This study aimed to compare a CAI model and a DL model for the detection of AF in patients undergoing electrocardiographic (ECG) examinations in tertiary healthcare centers. Methods Between December 2022 and November 2023, a total of 135,476 ECGs were performed, comprising 5,067 with AF and 130,409 without AF. The ECGs were analyzed using both artificial intelligence models. The obtained results were then compared to the gold standard (cardiologist's report). In the CAI model, signals were extracted from ECG images, analyzing five key parameters: cardiac rhythm, atrial depolarization, atrioventricular conduction, ventricular depolarization, and ventricular repolarization (figure 1A). These parameters were benchmarked against the standard values from the Brazilian Society of Cardiology guidelines for detecting cardiac anomalies. Conversely, the DL model utilized a one-dimensional ResNet-based Convolutional Neural Network (CNN). This model was trained using ADAM optimization and binary cross-entropy loss, enabling the learning of complex patterns in the data (figure 1B). Results The mean age was 54.6 years (71.9 years with AF and 53.9 without AF). In the AF population, 52.2% were male (46% were male in the overall sample). In the analysis conducted, the CAI model showed a sensitivity and specificity of 90% and 62%, respectively, while the DL model had 90% and 69%, respectively. ROC curves were generated for both models, demonstrating the superior performance of the DL model (figure 2A). Conclusions Although the sensitivity remained similar between the models, the DL model distinguished itself with higher specificity. These results suggest that artificial intelligence, particularly the deep learning approach, holds promise as a supportive resource in AF diagnosis. However, further studies are needed to evaluate the models more thoroughly and determine their clinical applicability in a broader context.Artificial intelligence modelsROC curves

Recognition Algorithm of AE Signal of Rock Fracture Based on Multiscale 1DCNN-BLSTM

Acoustic emission (AE) signals produced by different types of rocks have different characteristics of information. Determining the brittle mineral content of rock according to the acoustic emission characteristics of rock is helpful to understand the mechanical behavior of rock in field monitoring. This article constructs a deep learning algorithm model to identify acoustic emission signals released from rock fractures with different brittle mineral contents. In response to the interference characteristics of acoustic emission signal data, a multiscale one-dimensional convolutional neural network embedded with efficient channel attention (ECA) module was incorporated into the model, and multiscale convolutional kernels were used to extract features of different levels of precision. In the latter half of the model, the BLSTM network was incorporated to extract time series-related features, local spatial uncorrelated features, and weak periodic pattern features from the acoustic emission signal data. To solve the problem that the recognition accuracy of minority samples decreases, this study replaces ReLU activation function with SELU. The results show that the multiscale 1DCNN-BLSTM model embedded in ECA module has a good antinoise performance, and the recognition accuracy can reach over 90%. The discovery of this work provides a new idea for exploring the mechanism of rock mass instability.

1D-CNN: Classification of normal delivery and cesarean section types using cardiotocography time-series signals

Abstract Cardiotocography (CTG) is considered the gold standard for monitoring fetal heart rate (FHR) during pregnancy and labor to estimate the danger of oxygen deprivation. Visual interpretation of CTG traces is complex and frequently results in high rates of false positives and false negatives, leading to unfavorable and unwanted outcomes such as fetal mortality or needless cesarean surgery. If the data are well-balanced, which is uncommon in medical datasets, machine learning techniques can be helpful in interpretation. This study is designed to determine classification performance under various data balance approaches. We propose a robust methodology for the automated extraction of features that use a deep learning model based on the one-dimensional convolutional neural network (1D-CNN). We used a public database containing 552 intrapartum CTG recordings. Due to the imbalance in the dataset, the experiments were conducted under a variety of conditions such as (i) an unbalanced dataset, (ii) undersampling, (iii) a weighted binary cross-entropy approach, and (iv) oversampling utilizing the synthetic minority oversampling technique (SMOTE). We found an excellent sensitivity (99.80% for the unbalanced dataset, 96.25% for the weighted binary cross-entropy approach, and 99.81% with SMOTE) except for the under sampling situation, in which the sensitivity was 85.71%. Moreover, the 1D-CNN model incorporating SMOTE yielded promising results in 88% specificity, 93.72% quality index (QI), and 95.10% area under the curve. The model exhibited excellent performance in terms of sensitivity in every scenario except for undersampling. The oversampling of training data with SMOTE yielded a decent level of specificity, demonstrating the model’s strong predictive capacity. In addition, the SMOTE scenario resulted in fewer training epochs, which is another accomplishment.

A Multi-Step-Ahead Photovoltaic Power Forecasting Approach Using One-Dimensional Convolutional Neural Networks and Transformer

Due to environmental concerns about the use of fossil fuels, renewable energy, especially solar energy, is increasingly sought after for its ease of installation, cost-effectiveness, and versatile capacity. However, the variability in environmental factors poses a significant challenge to photovoltaic (PV) power generation forecasting, which is crucial for maintaining power system stability and economic efficiency. In this paper, a novel muti-step-ahead PV power generation forecasting model by integrating single-step and multi-step forecasts from various time resolutions was developed. One-dimensional convolutional neural network (CNN) layers were used for single-step forecasting to capture specific temporal patterns, with the transformer model improving multi-step forecasting by leveraging the combined outputs of the CNN. This combination can provide accurate and immediate forecasts as well as the ability to identify longer-term generation trends. Using the DKASC-ASA-1A and 1B datasets for empirical validation, several preprocessing methods were applied and a series of experiments were conducted to compare the performance of the model with other widely used deep learning models. The framework proved to be capable of accurately predicting multi-step-ahead PV power generation at multiple time resolutions.

Deep learning-based prediction of structural responses of RC slabs subjected to blast loading

Considering the risk of explosion, studying the dynamic structural behavior of reinforced concrete (RC) slabs subjected to blast loads is crucial for enhancing their resistance. Conventional approaches, including costly experimental tests, highly hypothetical analytical methods, and time-consuming numerical simulations, have their limitations. This study presents two deep learning-based models for rapid and accurate prediction of explosion-induced responses in RC slabs. Available literature data and supplemented numerical simulation data are used for training and testing. First, a multi-layer perceptron (MLP) model is established to predict the maximum displacement of RC slabs subjected to explosions. The input features include 10 parameters. The training results show that the MLP model exhibits good prediction performance. Second, a one-dimensional convolutional neural network (1D-CNN) model is constructed to predict the failure modes of RC slabs under explosive loads. The input features of the model are consistent with those of the MLP model. The 1D-CNN model outperforms the other five conventional machine learning models in classification. Furthermore, a permutation feature importance analysis is conducted to determine the effects of the 10 input features on the predicted outcomes. This analysis makes the predictions interpretable, thereby bolstering the credibility of the models. Results show that the proposed deep learning models offer an efficient and reliable method to predict the structural response of RC slabs under explosion loads.