SAE Model Research Articles

A feature reconstruction and SAE model based diagnosis method for multiple mixed faults

Owing to the merits of automatic feature extraction and depth structure, intelligent fault diagnosis based on deep neural networks has become a great concern. However, the non-fault state monitoring data volume of actual industrial machinery is rich, whereas the fault state data volume is insufficient and weak. Furthermore, achieving multiple mixed-fault diagnoses using skewed data distributions is extremely difficult. A feature reconstruction and sparse auto-encoder (AE) model-based diagnosis method for multiple mixed faults is proposed in this study to bridge these gaps. Such a feature reconstruction algorithm is designed and employed to address the following issues: (1) expensive computing resulting from the long sequential features of vibration monitoring data and (2) the extraction problem caused by the submersion of scarce data features. Furthermore, an adaptive loss function was formulated, and a deep AE network was constructed to identify the health status and determine the fault level. Diagnoses of artificial and real faults verify the availability and superiority of the proposed scheme, demonstrating the adaptability and robustness of these hyperparameters.

Lipid peroxidation-induced ferroptosis as a therapeutic target for mitigating neuronal injury and inflammation in sepsis-associated encephalopathy: insights into the hippocampal PEBP-1/15-LOX/GPX4 pathway

BackgroundSepsis-associated encephalopathy (SAE) refers to the widespread impairment of brain function caused by noncentral nervous system infection mediated by sepsis. Lipid peroxidation-induced ferroptosis contributes to the occurrence and course of SAE. This study aimed to investigate the relationship between neuronal injury and lipid peroxidation-induced ferroptosis in SAE.MethodsBaseline data were collected from pediatric patients upon admission, and the expression levels of various markers related to lipid peroxidation and ferroptosis were monitored in the serum and peripheral blood mononuclear cells (PBMCs) of patients with SAE as well as SAE model mice. The hippocampal phosphatidylethanolamine-binding protein (PEBP)-1/15-lysine oxidase (LOX)/ glutathione peroxidase 4 (GPX4) pathway was assessed for its role on the inhibitory effect of ferroptosis in SAE treatment.ResultsThe results showed elevated levels of S100 calcium-binding protein beta (S-100β), glial fibrillary acidic protein, and malondialdehyde in the serum of SAE patients, while superoxide dismutase levels were reduced. Furthermore, analysis of PBMCs revealed increased transcription levels of PEBP1, LOX, and long-chain fatty acyl-CoA synthetase family member 4 (ACSL4) in SAE patients, while the transcription levels of GPX4 and cystine/glutamate transporter xCT (SLC7A11) were decreased. In comparison to the control group, the SAE mice exhibited increased expression of S-100β and neuron-specific enolase (NSE) in the hippocampus, whereas the expression of S-100β and NSE were reduced in deferoxamine (DFO) mice. Additionally, iron accumulation was observed in the hippocampus of SAE mice, while the iron ion levels were reduced in the DFO mice. Inhibition of ferroptosis alleviated the mitochondrial damage (as assessed by transmission electron microscopy, hippocampal mitochondrial ATP detection, and the JC-1 polymer-to-monomer ratio in the hippocampus) and the oxidative stress response induced by SAE as well as attenuated neuroinflammatory reactions. Further investigations revealed that the mechanism underlying the inhibitory effect of ferroptosis in SAE treatment is associated with the hippocampal PEBP-1/15-LOX/GPX4 pathway.ConclusionThese results offer potential therapeutic targets for the management of neuronal injury in SAE and valuable insights into the potential mechanisms of ferroptosis in neurological disorders.

Typical fault prediction method for wind turbines based on an improved stacked autoencoder network

Abstract Timely prediction of wind turbine states is valuable for reduction of potential significant losses resulting from deterioration of health condition. To enhance the accuracy of fault diagnosis and early warning, data collected from supervisory control and data acquisition (SCADA) system of wind turbines is graphically processed and used as input for a deep learning mode, which effectively reflects the correlation between the faults of different components of wind turbines and the multi-state information in SCADA data. An improved stacked autoencoder (ISAE) framework is proposed to address the issue of ineffective fault identification due to the scarcity of labeled samples for certain fault types. In the data augmentation module, synthetic samples are generated using SAE to enhance the training data. Another SAE model is trained using the augmented dataset in the data prediction module for future trend prediction. The attribute correlation information is embedded to compensate for the shortcomings of SAE in learning attribute relationships, and the optimal factor parameters are searched using the particle swarm optimization (PSO) algorithm. Finally, the state of wind turbines is predicted using a CNN-based fault diagnosis module. Experimental results demonstrate that the proposed method can effectively predict faults and identify fault types in advance, which is helpful for wind farms to take proactive measures and schedule maintenance plans to avoid significant losses.

Oxytocin alleviates cognitive and memory impairments by decreasing hippocampal microglial activation and synaptic defects via OXTR/ERK/STAT3 pathway in a mouse model of sepsis-associated encephalopathy

BackgroundSepsis-associated encephalopathy (SAE) is a diffuse brain dysfunction, characterized by cognitive and memory impairments closely linked to hippocampal dysfunction. Though it is well-known that SAE is a diffuse brain dysfunction with microglial activation, the pathological mechanisms of SAE are not well established and effective clinical interventions are lacking. Oxytocin (OXT) is reported to have anti-inflammatory and neuroprotective roles. However, the effects of OXT on SAE and the underlying mechanisms are not clear. MethodsSAE was induced in adult C57BL/6J male mice by cecal ligation and perforation (CLP) surgery. Exogenous OXT was intranasally applied after surgery. Clinical score, survivor rate, cognitive and memory behaviors, and hippocampal neuronal and non-neuronal functions were evaluated. Cultured microglia challenged with lipopolysaccharide (LPS) were used to investigate the effects of OXT on microglial functions, including inflammatory cytokines release and phagocytosis. The possible intracellular signal pathways involved in the OXT-induced neuroprotection were explored with RNA sequencing. ResultsHippocampal OXT level decreases, while the expression of OXT receptor (OXTR) increases around 24 h after CLP surgery. Intranasal OXT application at a proper dose increases mouse survival rate, alleviates cognitive and memory dysfunction, and restores hippocampal synaptic function and neuronal activity via OXTR in the SAE model. Intraperitoneal or local administration of the OXTR antagonist L-368,899 in hippocampal CA1 region inhibited the protective effects of OXT. Moreover, during the early stages of sepsis, hippocampal microglia are activated, while OXT application reduces microglial phagocytosis and the release of inflammatory cytokines, thereby exerting a neuroprotective effect. OXT may improve the SAE outcomes via the OXTR-ERK-STAT3 signaling pathway. ConclusionOur study uncovers the dysfunction of the OXT signal in SAE and shows that intranasal OXT application at a proper dose can alleviate SAE outcomes by reducing microglial overactivation, suggests that OXT may be a promising therapeutic approach in managing SAE patients.

Mast cell activation mediates blood-brain barrier impairment and cognitive dysfunction in septic mice in a histamine-dependent pathway.

Sepsis-associated encephalopathy (SAE) is a diffuse cerebral dysfunction resulting from a systemic inflammatory response to infection; however, its pathophysiology remains unclear. Sepsis-induced neuroinflammation and blood-brain barrier (BBB) disruption are crucial factors in brain function disturbance in SAE. Mast cells (MCs) activation plays an important role in several neuroinflammation models; however, its role in SAE has not been comprehensively investigated. We first established a SAE model by cecal ligation puncture (CLP) surgery and checked the activation of MCs. MCs activation was checked using immumohistochemical staining and Toluidine Blue staining. We administrated cromolyn (10mg/ml), a MC stabilizer, to rescue the septic mice. Brain cytokines levels were measured using biochemical assays. BBB disruption was assessed by measuring levels of key tight-junction (TJ) proteins. Cognitive function of mice was analyzed by Y maze and open field test. Transwell cultures of brain microvascular endothelial cells (BMVECs) co-cultured with MCs were used to assess the interaction of BMVECs and MCs. Results showed that MCs were overactivated in the hippocampus of CLP-induced SAE mice. Cromolyn intracerebroventricular (i.c.v) injection substantially inhibited the MCs activation and neuroinflammation responses, ameliorated BBB impairment, improved the survival rate and alleviated cognitive dysfunction in septic mice. In vitro experiments, we revealed that MCs activation increased the sensitivity of BMVECs against to lipopolysaccharide (LPS) challenge. Furthermore, we found that the histamine/histamine 1 receptor (H1R) mediated the interaction between MCs and BMVECs, and amplifies the LPS-induced inflammatory responses in BMVECs by modulating the TLR2/4-MAPK signaling pathway. MCs activation could mediate BBB impairment and cognitive dysfunction in septic mice in a histamine-dependent pathway.

MiRNA-494 specifically inhibits SIRT3-mediated microglia activation in sepsis-associated encephalopathy.

BackgroundSepsis-associated encephalopathy (SAE) is characterized by the activation of inflammatory cascades, in which microglia play a key role. The activation of Recombinant Sirtuin 3 (SIRT3) was shown to significantly reduce the susceptibility of microglia to inflammatory stress. The purpose of this study is to determine whether miRNA-494 can regulate the activation and oxidative stress of SAE microglia through SIRT3.MethodsAn SAE rat model was established, and the expression of Ionized calcium bindingadaptor molecule-1 (Iba-1) in rat brain tissue was detected by immunohistochemistry. Enzyme-linked immuno sorbent assay was performed to detect the expression of tumor necrosis factor alpha (TNF-α) and interleukin-6 (IL-6) in brain tissue. Real time quantitative PCR was performed to detect the relative expression of SIRT3 and related miRNAs, while Western blot was used to detect the protein expression of SIRT3. Rat microglia cells were cultured in vitro. After miRNA-494 was transfected, the expression of TNF-α and IL-6 was detected. Western blot was used to detect the protein expression of SIRT3 and Iba-1 in microglia.ResultsThe results showed that the expression of Iba-1 in the brain tissue of the SAE model group increased, and the expression of inflammatory factors TNF-α and IL-6 increased significantly (P<0.01). The expression of SIRT3 protein and mRNA in the brain tissue of the SAE model group also significantly increased (P<0.05). The relative expression of miRNA-494 in the SAE model group was significantly lower than that in the control group (P<0.01). After miRNA-494 was transfected into microglia, cells were treated with lipopolysaccharide. In the miRNA transfection group, the expression levels of TNF-α and IL-6 were significantly lower than those in the negative control (NC) group (P<0.01), and the protein expression levels of Iba-1 and SIRT3 were also significantly lower than those in the NC (P<0.01).ConclusionsMiRNA-494 may further regulate the activation of microglia in SAE by regulating mitochondrial function, providing basic research data for the development of new SAE treatment methods.

Artificial Intelligence-Enabled Cyberbullying-Free Online Social Networks in Smart Cities

In recent years, smart city services have moved the existence of people from the physical to the virtual world (cyberspace), e.g., online banking, e-commerce, telemedicine, etc. Along with the benefits of smart cities, the problems of the physical world are also moved to the cyber world, like cyberbullying in online social networks (OSN). Automated cyberbullying detection techniques need to be designed to remove the potential tragedies in OSNs. The recent advent of artificial intelligence (AI) models like machine learning and deep learning (DL) models can be employed for the detection of cyberbullying in the OSN. With this motivation, this paper develops an AI-enabled cyberbullying-free OSN (AICBF-ONS) technique in smart cities. The proposed AICBF-ONS technique involves chaotic salp swarm optimization (CSSO)-based feature selection technique to derive a useful set of features from the OSN data. In addition, stacked autoencoder model is used as a classification model to allocate appropriate class labels of the OSN data. To improve the detection performance of the SAE model, a parameter tuning process take place using the mayfly optimization (MFO) algorithm. An extensive experimental analysis ensured the supremacy of the proposed AICBF-ONS technique.

Optimized Stacked Autoencoder for IoT Enabled Financial Crisis Prediction Model

Recently, Financial Technology (FinTech) has received more attention among financial sectors and researchers to derive effective solutions for any financial institution or firm. Financial crisis prediction (FCP) is an essential topic in business sector that finds it useful to identify the financial condition of a financial institution. At the same time, the development of the internet of things (IoT) has altered the mode of human interaction with the physical world. The IoT can be combined with the FCP model to examine the financial data from the users and perform decision making process. This paper presents a novel multi-objective squirrel search optimization algorithm with stacked autoencoder (MOSSA-SAE) model for FCP in IoT environment. The MOSSA-SAE model encompasses different subprocesses namely pre-processing, class imbalance handling, parameter tuning, and classification. Primarily, the MOSSA-SAE model allows the IoT devices such as smartphones, laptops, etc., to collect the financial details of the users which are then transmitted to the cloud for further analysis. In addition, SMOTE technique is employed to handle class imbalance problems. The goal of MOSSA in SMOTE is to determine the oversampling rate and area of nearest neighbors of SMOTE. Besides, SAE model is utilized as a classification technique to determine the class label of the financial data. At the same time, the MOSSA is applied to appropriately select the ‘weights’ and ‘bias’ values of the SAE. An extensive experimental validation process is performed on the benchmark financial dataset and the results are examined under distinct aspects. The experimental values ensured the superior performance of the MOSSA-SAE model on the applied dataset.

An Alternative Procedure to Produce a P-Spline Small Area Estimation Model Based on Partial Residual Plot and Significance Test of Spline Term

This study provides an alternative procedure to produce the penalized spline small area estimation (P-Spline SAE) model by plotting each of auxiliary variable and variable interest as a simple nonlinearity identification and performing the iterative procedure: by estimating the model, producing partial residual plots to check model adequacy and also identify the nonlinearity, and testing the significance of spline term using Restricted Likelihood Ratio Test (RLRT). These procedures are applied to estimate the monthly average per-capita expenditure of district level in the Province of Bali, 2014 using direct survey estimates from the National Socio-Economic Survey (Susenas 2014) and auxiliary variables from the administrative record of village data (PODES 2014). The Fay-Herriot (FH) model (M1) as a benchmark and four P-Spline SAE model, i.e. the P-Spline SAE with spline term: x2 and x3 (M2), x3 and x4 (M3), x2, x3 and x4 (M4), and x1, x2, x3 and x4 (M5), are obtained. From RLRT, the spline term of M3, M4, and M5 are statistically significant. According to the parametric bootstrap of mean squared prediction error (MSPE) and coefficient of variation (CV), the M4 and M5 show a significant improvement with the CV values range from about 1%-6% compared to M1 with a range from about 4%-17%, shows that these two models more efficient. The M3 model shows the opposite performance even though has the smallest AIC value. More detail, the MSPE and CV produced by M4 are slightly better than M5 makes the M4 is the best model in this study.

A Just-in-Time Fine-Tuning Framework for Deep Learning of SAE in Adaptive Data-Driven Modeling of Time-Varying Industrial Processes

In modern industrial processes, soft sensors have played increasingly important roles for effective process monitoring, control and optimization. Deep learning has shown excellent ability for hierarchical nonlinear feature representation in soft sensors. However, the existing deep learning based soft sensors are mostly trained offline and applied online without updating mechanism. This may cause their performance degradation in time-varying processes. To deal with this problem, an adaptive updating framework is proposed for deep learning, which is based on just-in-time fine-tuning of stacked autoencoder (JIT-SAE). In JIT-SAE, an offline SAE model is first trained with layer-wise unsupervised pre-training and supervised fine tuning. For online prediction, the network is dynamically fine-tuned upon the query sample. For each query sample, the most relevant labeled samples are selected to form a fine-tuning dataset from the historical labeled database, which is regularly augmented once new labeled samples are available from laboratory analysis. Moreover, each relevant sample is assigned with a weight according to its similarity with the query sample. Then, the deep network is fine-tuned with these relevant labeled samples by designing a weighted loss function. Thus, JIT-SAE is able to track the newest process running state timely and match the data pattern accurately. Case study on an industrial hydrocracking process is provided to demonstrate the effectiveness of the JIT-SAE framework.

Ellipticity dependence of excitation and ionization of argon atoms by short-pulse infrared radiation

When atoms or molecules are exposed to strong short-pulse infrared radiation, ionization as well as "frustrated tunneling ionization" (FTI) can occur, in which a portion of the almost ionized electrons recombine into the initial ground or an excited bound state. We analyze the ellipticity dependence of the relative signals that are predicted in a single-active electron approximation (SAE), the validity of which is checked against a parameter-free multi-electron \hbox{$R$-matrix} (close-coupling) with time dependence approach. We find good agreement between the results from both models, thereby providing confidence in the SAE model potential to treat the process of interest. Comparison of the relative excitation probabilities found in our numerical calculations with the predictions of Landsman {\it et al.}\ (New Journal of Physics {\bf 15} (2013) 013001) and Zhao {\it et al.}\ (Optics Express {\bf 27} (2019) 21689) reveals good agreement with the former for short pulses. For longer pulses, the ellipticity dependence becomes wider than that obtained from the Landsman {\it et al.} formula, but we do not obtain the increase compared to linearly polarized radiation predicted by Zhao {\it et al.}

Wykorzystywanie polskich i międzynarodowych doświadczeń w innowacyjnym programie plastycznej edukacji wczesnoszkolnej (wnioski z pierwszego roku realizacji programu)

&lt;p&gt;Opisane w opracowaniu badania są pokłosiem międzynarodowego projektu badawczo-dydaktycznego „Nauka-Sztuka-Edukacja. Innowacyjny model diagnozy, metod, form pracy i opieki nad uczniem zdolnym plastycznie” (projekt współfinansowany przez UE, październik 2011 – wrzesień 2013). Autorka po zakończeniu projektu prowadziła trzyletnie badania (2015–2018) nad efektywnością modelu NSE (mającego służyć rozwojowi umiejętności życiowych dzieci) w 12 szkołach podstawowych Polski południowej. W niniejszym artykule autorka dzieli się pierwszymi wnioskami z badań, dotyczącymi możliwości wpływu modelu NSE na wzrost umiejętności współpracy dzieci w młodszym wieku szkolnym i pokonywania stresu w sytuacjach trudnych. W tym celu zostały omówione wyniki badań eksperymentalnych, w których uczestniczyło 126 dzieci z trzech środowisk (duże miasto, małe miasto, wieś) po roku realizacji modelu NSE w szkołach w klasie I szkoły podstawowej. Wyniki przynoszą optymistyczne dane, cieszy fakt wzrostu w grupach eksperymentalnych strategii współpracy przy obniżeniu strategii obronnych, niekorzystnych dla dalszego zdrowia psychicznego dzieci: uniku, ulegania, agresji.&lt;/p&gt;

The GTU: A New Realistic Generic Pickup Truck and SUV Model

&lt;div class="section abstract"&gt;&lt;div class="htmlview paragraph"&gt;Traditionally, ground vehicle aerodynamics has been researched with highly simplified models such as the Ahmed body and the SAE model. These models established and advanced the fundamental understanding of bluff body aerodynamics and have generated a large body of published data, however, their application to the development of passenger vehicles is limited by the highly idealized nature of their geometries. To date, limited data has been openly published on aerodynamic investigations of production vehicles, most likely due to the proprietary nature of production vehicle geometry. In 2012, Heft et al. introduced the realistic generic car model ‘DrivAer’ that better represents the flow physics associated with a typical production vehicle. The introduction of the DrivAer model has led to a broad set of published data for both experimental and computational investigations and has proven itself invaluable as a correlation and calibration tool of wind tunnels, the validation of computational fluid dynamics (CFD) codes and increasing the understanding of the fundamental flow physics around passenger vehicles.&lt;/div&gt;&lt;div class="htmlview paragraph"&gt;Automotive sales trends in the United States, published by the Bureau of Economic Analysis in 2018, indicate that sales of Pickup Trucks (PUs) and Sports Utility Vehicles (SUVs) have increased over the past 10 years and are outselling sedans at a rate just over two to one. Compared to sedans, PU and SUV body styles pose additional aerodynamic challenges due to their complex wake structures. The introduction of a realistic generic PU and SUV model as an open access tool is expected to yield benefits to the wider community, equivalent to those of the DrivAer passenger vehicle. This paper introduces the Generic Truck Utility (GTU) as a realistic, generic PU truck and interchangeable SUV model. The paper will focus on the design and development of the GTU and will present a summary of preliminary experimental results of the GTU complemented by numerical simulations using iconCFD®, an open source based CFD solver.&lt;/div&gt;&lt;/div&gt;

Data-Enhanced Stacked Autoencoders for Insufficient Fault Classification of Machinery and its Understanding via Visualization

As a practical tool for big data processing, deep learning not only has drawn extensive attentions in the inherent law and representation level of sample data, but also has been widely concerned in the field of mechanical intelligent fault diagnosis. In deep learning models, autoencoder (AE) and its derivative models can automatically extract useful features from big data, and many researchers have successfully applied them to the field of intelligent fault diagnosis. However, these studies always neglect two important points as follows: (1) the model training process will not be ideal when the original training dataset is insufficient; (2) the learning content of the network model is not clear. In order to surmount the above deficiencies, this paper proposes a novel framework named Data-enhanced Stacked Autoencoders (DESAE), which consists of a data enhancement module and a fault classification module. In the data enhancement module, SAE is adopted to generate simulated signals to strengthen the insufficient training data. In the fault classification module, the enhanced dataset is used to train another SAE model for fault type recognition. Meanwhile, two bearing datasets are employed to validate the efficiency of the proposed method. The experimental results show that the proposed method is superior to the method without enhanced data. In addition, the visual analysis of the learning characteristics in each layer of DESAE is presented, which is helpful to understand the working process of DESAE.

Link Quality Estimation Method for Wireless Sensor Networks Based on Stacked Autoencoder

In wireless sensor networks, effective link quality estimation is the basis of topology management and routing control. Effective link quality estimation can guarantee the transmission of data, as well as improve the throughput rate, and hence, extend the life of the entire network. For this reason, a stacked autoencoder-based link quality estimator (LQE-SAE) is proposed. Specifically, the zero-filling method is developed to process the original missing link information. Then, the SAE model is used to extract the asymmetric characteristics of the uplink and downlink from the received signal strength indicator, link quality indicator, and signal-to-noise ratio, respectively. These characteristics are fused by SAE to construct the link features' vectors, which are given as inputs to the support vector classifier (SVC), for which the link quality grade is taken as its label. The experimental results in different scenarios show that the LQE-SAE has better accuracy than link quality estimators based on the SVC, ELM, and WNN.

Using a stacked-autoencoder neural network model to estimate sea state bias for a radar altimeter.

This paper constructed a stacked-autoencoder neural network model (SAE model) to estimate sea state bias (SSB) based on radar altimeter data. Six cycles of the geophysical data record (GDR) from Jason-1/2 radar altimeters were used as a training dataset, and the other 2 cycles of the GDR from Jason-1/2 were used for testing. The inputs to this SAE model include the significant wave height (SWH), wind speed (U), sea surface height (SSH), backscatter coefficient (σ0) and automatic gain control (AGC), and the model outputs the SSB. The model includes one input layer, three hidden layers and one output layer. The SSBs in the GDR of Jason-1/2 were obtained from a nonparametric model based on the SWH and U as input variables; thus, the model has high accuracy but low efficiency. The SSBs in the GDR of HY-2A were computed using a four-parameter parametric model that uses the SWH and U as input variables; therefore, this model’s computational speed is high but its accuracy is low. Thus, we used the HY-2A radar altimeter as an unseen validation dataset to evaluate the performance of the SAE model. Then, we analyzed the contrasting results of these methods, including the differences in the SSB, explained variance, residual error and operational efficiency. The results demonstrate not only that the accuracy of the SAE model is superior to that of the conventional parametric model but also that its operational efficiency is better than that of the nonparametric model.

차간 거리가 주행차량의 공력특성에 미치는 영향에 관한 수치해석 연구

Aerodynamic design of a vehicle has very important meaning on the fuel economy, dynamic stability and the noise & vibration of a moving vehicle. In this study, the correlation of aerodynamic effect between two model vehicles moving inline on a road was studied with the basic SAE model vehicle. Drag and lift are two main physical forces acting on the vehicle and both of them directly effect on the fuel economy and driving stability of the vehicle.For the research, the distance between two vehicles is varied from 5m to 30m at the fixed vehicle speed, 100km/h and the side-wind was assumed to be zero. The main issue for this numerical research is on the understanding of the interaction forces; lift and drag between two vehicles formed inline.From the study, it was found that as the distance between two vehicles is closer, the drag force acting on both the front and rear vehicle decreases and the lift force has same trend for both vehicle. As the distance(D) is 5m, the drag of the front vehicle reduced 7.4% but 28.5% for the rear-side vehicle. As the distance is 30m, the drag of the rear vehicle is still reduced to 22% compared to the single driving.