RESUMEN
In tunnel boring projects, wear and tear in the tooling system can have significant consequences, such as decreased boring efficiency, heightened maintenance costs, and potential safety hazards. In this paper, a fault diagnosis method for TBM tooling systems based on SAV-SVDD failure location (SSFL) is proposed. The aim of this method is to detect faults caused by disk cutter wear during the boring process, which diminishes the boring efficiency and is challenging to detect during construction. This paper uses SolidWorks to create a complete three-dimensional model of the TBM hydraulic thrust system and tool system. Then, dynamic simulations are performed with Adams. This helps us understand how the load on the propulsion hydraulic cylinder changes as the TBM tunneling tool wears to different degrees during construction. The hydraulic propulsion system was modeled and simulated using AMESIM software. Utilizing the load on the hydraulic propulsion cylinder as an input signal, pressure signals from the two chambers of the hydraulic cylinder and the system's flow signal were acquired. This enabled an in-depth exploration of the correlation between these acquired signals and the extent of the tooling system failure. Following this analysis, a collection of normal sample data and sample data representing different degrees of disk cutter abrasions was amassed for further study. Next, an SSFL network model for locating the failure area of the cutter was established. Fault sample data were used as the input, and the accuracy of the fault diagnosis model was tested. The test results show that the performance of the SSFL network model is better than that of the SAE-SVM and SVDD network models. The SSFL model achieves 90% accuracy in determining the failure area of the cutter head. The model effectively identifies the failure regions, enabling timely tool replacement to avoid decreased boring efficiency under wear conditions. The experimental findings validate the feasibility of this approach.
RESUMEN
Motor imagery (MI) brain-computer interface (BCI) assist users in establishing direct communication between their brain and external devices by decoding the movement intention of human electroencephalogram (EEG) signals. However, cerebral cortical potentials are highly rhythmic and sub-band features, different experimental situations and subjects have different categories of semantic information in specific sample target spaces. Feature fusion can lead to more discriminative features, but simple fusion of features from different embedding spaces leading to the model global loss is not easily convergent and ignores the complementarity of features. Considering the similarity and category contribution of different sub-band features, we propose a multi-band centroid contrastive reconstruction fusion network (MB-CCRF). We obtain multi-band spatio-temporal features by frequency division, preserving the task-related rhythmic features of different EEG signals; use a multi-stream cross-layer connected convolutional network to perform a deep feature representation for each sub-band separately; propose a centroid contrastive reconstruction fusion module, which maps different sub-band and category features into the same shared embedding space by comparing with category prototypes, reconstructing the feature semantic structure to ensure that the global loss of the fused features converges more easily. Finally, we use a learning mechanism to model the similarity between channel features and use it as the weight of fused sub-band features, thus enhancing the more discriminative features, suppressing the useless features. The experimental accuracy is 79.96% in the BCI competition â £-â ¡a dataset. Moreover, the classification effect of sub-band features of different subjects is verified by comparison tests, the category propensity of different sub-band features is verified by confusion matrix tests and the distribution in different classes of each sub-band feature and fused feature are showed by visual analysis, revealing the importance of different sub-band features for the EEG-based MI classification task.
Asunto(s)
Encéfalo , Electroencefalografía , Humanos , Comunicación , Aprendizaje , MovimientoRESUMEN
Heterogeneous photocatalysis coupled with peroxymonosulfate (PMS) activation is considered as an advanced water purification technology for emerging contaminates degradation. In this study, Cobalt (Co) doped nitrogen-vacancies-rich C3N5 photocatalysts (Co/Nv-C3N5) were designed to activate PMS for tetracycline removal. The photo-chemical oxidation system displayed superior advantage, in which the observed rate constant of tetracycline degradation (0.1488 min-1) was 10.86 and 1.82 times higher than that of photo-oxidation and chemical-oxidation systems. Density functional theory calculation results verified the reconstruction of local charge distribution during PMS activation, indicating Co doping and nitrogen-vacancy engineering not only promoted photoelectrons capture, but also boosted electron transfer from the C-N framework to PMS and the generation of active species. Furthermore, several unique multiple electron transfer mechanisms were found in nonradicals (h+, 1O2 and Co(IV)) pathways. Additionally, three possible tetracycline degradation pathways were proposed and the toxicity of the intermediates was evaluated. Overall, the findings from this study provided a novel strategy for developing high-efficient photocatalyst for the rapid degradation of organic pollutants.
Asunto(s)
Electrones , Compuestos Heterocíclicos , Tetraciclina , Antibacterianos , Cobalto , Nitrógeno , PeróxidosRESUMEN
Glioblastoma is acknowledged as the most aggressive cerebral tumor in adults. However, the efficacy of current standard therapy is seriously undermined by drug resistance and suppressive immune microenvironment. Ferroptosis is a recently discovered form of iron-dependent cell death that may have excellent prospect as chemosensitizer. The utilization of ferropotosis inducer Erastin could significantly mediate chemotherapy sensitization of Temozolomide and exert anti-tumor effects in glioblastoma. In this study, a combination of hydrogel-liposome nanoplatform encapsulated with Temozolomide and ferroptosis inducer Erastin was constructed. The αvß3 integrin-binding peptide cyclic RGD was utilized to modify codelivery system to achieve glioblastoma targeting strategy. As biocompatible drug reservoirs, cross-linked GelMA (gelatin methacrylamide) hydrogel and cRGD-coated liposome realized the sustained release of internal contents. In the modified intracranial tumor resection model, GelMA-liposome system achieved slow release of Temozolomide and Erastin in situ for more than 14 d. The results indicated that nanoplatform (T+E@LPs-cRGD+GelMA) improved glioblastoma sensitivity to chemotherapeutic temozolomide and exerted satisfactory anti-tumor effects. It was demonstrated that the induction of ferroptosis could be utilized as a therapeutic strategy to overcome drug resistance. Furthermore, transcriptome sequencing was conducted to reveal the underlying mechanism that the nanoplatform (T+E@LPs-cRGD+GelMA) implicated in. It is suggested that GelMA-liposome system participated in the immune response and immunomodulation of glioblastoma via interferon/PD-L1 pathway. Collectively, this study proposed a potential combinatory therapeutic strategy for glioblastoma treatment.
RESUMEN
In recent years, with the rapid development of deep learning, various deep learning frameworks have been widely used in brain-computer interface (BCI) research for decoding motor imagery (MI) electroencephalogram (EEG) signals to understand brain activity accurately. The electrodes, however, record the mixed activities of neurons. If different features are directly embedded in the same feature space, the specific and mutual features of different neuron regions are not considered, which will reduce the expression ability of the feature itself. We propose a cross-channel specific-mutual feature transfer learning (CCSM-FT) network model to solve this problem. The multibranch network extracts the specific and mutual features of brain's multiregion signals. Effective training tricks are used to maximize the distinction between the two kinds of features. Suitable training tricks can also improve the effectiveness of the algorithm compared with novel models. Finally, we transfer two kinds of features to explore the potential of mutual and specific features to enhance the expressive power of the feature and use the auxiliary set to improve identification performance. The experimental results show that the network has a better classification effect in the BCI Competition IV-2a and the HGD datasets.
RESUMEN
Extracellular DNA (eDNA), as a dynamic repository for antibiotic-resistant genes (ARGs), is a rising threat to public health. This work used a ball-milling method to enhance defect structures of activated carbon, and carbon defects exhibited an excellent capacity in persulfate (PS) activation for model eDNA and real ARGs degradation. The eDNA removal by defect-rich carbon with PS was 2.3-fold higher than that by unmilled activated carbon. The quenching experiment, electrochemical analysis and thermodynamic calculation showed that carbon defects could not only enhance the generation of SO4â¢- and â¢OH, but formed an electron transfer bridge between eDNA and PS, leading to the non-radical oxidation of eDNA. According to molecular calculations, the nitrogenous bases of DNA were the easiest sites to be oxidized by electron transfer pathway. This research offers a new way using defective carbon materials as PS activator for eDNA pollutants, and an insight into the non-radical mechanism of eDNA degradation.
Asunto(s)
Contaminantes Químicos del Agua , Contaminantes Químicos del Agua/química , Carbón Orgánico , Electrones , Sulfatos/química , Oxidación-Reducción , ADNRESUMEN
Surface electromyogram (sEMG) signals have been used in human motion intention recognition, which has significant application prospects in the fields of rehabilitation medicine and cognitive science. However, some valuable dynamic information on upper-limb motions is lost in the process of feature extraction for sEMG signals, and there exists the fact that only a small variety of rehabilitation movements can be distinguished, and the classification accuracy is easily affected. To solve these dilemmas, first, a multiscale time-frequency information fusion representation method (MTFIFR) is proposed to obtain the time-frequency features of multichannel sEMG signals. Then, this paper designs the multiple feature fusion network (MFFN), which aims at strengthening the ability of feature extraction. Finally, a deep belief network (DBN) was introduced as the classification model of the MFFN to boost the generalization performance for more types of upper-limb movements. In the experiments, 12 kinds of upper-limb rehabilitation actions were recognized utilizing four sEMG sensors. The maximum identification accuracy was 86.10% and the average classification accuracy of the proposed MFFN was 73.49%, indicating that the time-frequency representation approach combined with the MFFN is superior to the traditional machine learning and convolutional neural network.
Asunto(s)
Movimiento , Extremidad Superior , Electromiografía , Humanos , Movimiento (Física) , Redes Neurales de la ComputaciónRESUMEN
Brain-computer interface (BCI) based on motor imagery (MI) electroencephalogram (EEG) decoding helps motor-disabled patients to communicate with external devices directly, which can achieve the purpose of human-computer interaction and assisted living. MI EEG decoding has a core problem which is extracting as many multiple types of features as possible from the multi-channel time series of EEG to understand brain activity accurately. Recently, deep learning technology has been widely used in EEG decoding. However, the variability of the simple network framework is insufficient to satisfy the complex task of EEG decoding. A multi-scale fusion convolutional neural network based on the attention mechanism (MS-AMF) is proposed in this paper. The network extracts spatio temporal multi-scale features from multi-brain regions representation signals and is supplemented by a dense fusion strategy to retain the maximum information flow. The attention mechanism we added to the network has improved the sensitivity of the network. The experimental results show that the network has a better classification effect compared with the baseline method in the BCI Competition IV-2a dataset. We conducted visualization analysis in multiple parts of the network, and the results show that the attention mechanism is also convenient for analyzing the underlying information flow of EEG decoding, which verifies the effectiveness of the MS-AMF method.
Asunto(s)
Interfaces Cerebro-Computador , Algoritmos , Electroencefalografía , Humanos , Imaginación , Redes Neurales de la ComputaciónRESUMEN
Recognition of motor imagery intention is one of the hot current research focuses of brain-computer interface (BCI) studies. It can help patients with physical dyskinesia to convey their movement intentions. In recent years, breakthroughs have been made in the research on recognition of motor imagery task using deep learning, but if the important features related to motor imagery are ignored, it may lead to a decline in the recognition performance of the algorithm. This paper proposes a new deep multi-view feature learning method for the classification task of motor imagery electroencephalogram (EEG) signals. In order to obtain more representative motor imagery features in EEG signals, we introduced a multi-view feature representation based on the characteristics of EEG signals and the differences between different features. Different feature extraction methods were used to respectively extract the time domain, frequency domain, time-frequency domain and spatial features of EEG signals, so as to made them cooperate and complement. Then, the deep restricted Boltzmann machine (RBM) network improved by t-distributed stochastic neighbor embedding(t-SNE) was adopted to learn the multi-view features of EEG signals, so that the algorithm removed the feature redundancy while took into account the global characteristics in the multi-view feature sequence, reduced the dimension of the multi-visual features and enhanced the recognizability of the features. Finally, support vector machine (SVM) was chosen to classify deep multi-view features. Applying our proposed method to the BCI competition IV 2a dataset we obtained excellent classification results. The results show that the deep multi-view feature learning method further improved the classification accuracy of motor imagery tasks.