Search

Aiming at the problem of precision driving and vibration suppression for sensitive payloads on-orbit, this paper proposes a new compliant platform based on an embedded superstructure and a smart material actuator. Firstly, the main structure of the platform is designed and optimized to achieve the expected indicators via the response surface method. Then, the vibration reduction mechanism of the platform with the embedded superstructure is studied by establishing an equivalent model. Following that, a four-phase superstructure is matched and designed with a compact space, and the results are verified by finite element modal analysis. Finally, both the tensioning performance and vibration reduction performance under fixed frequency harmonic disturbance are studied via transient dynamic simulation. Based on the obtained results, directions for future improvements are proposed. The relevant conclusions can provide a reference for function integration of precision tensioning and vibration suppression.

ObjectiveTo understand the renal damage and clinical features of pediatric patients with acute Epstein-Barr virus (EBV) infectionMethodsIn this retrospective observational study, 548 pediatric patients who were admitted to and treated at the Xiamen Women and Children Health Center between January 2017 and December 2021 and who met the criteria of acute EBV infection were selected as participants. The sociodemographic and clinical data of these patients were collected for statistical analysis. The study population was divided into a renal damage group (41 patients) and a non-renal damage group (507 patients), and the characteristics of the two groups were compared.Results(1) Of the 548 enrolled patients, 340 and 208 were boys and girls, respectively. Among them, 41 patients showed renal damage (renal damage group), including 26 boys and 15 girls, and the incidence rate of renal damage was 7.48%. (2) The major renal involvements in the 41 pediatric patients with acute EBV infection in the renal damage group manifested as hematuria (56.1%), proteinuria (37.71%), hematuria + proteinuria (12.9%), edema (51.22%), hypertension (17.07%), oliguria (4.88%), and acute renal failure (2.44%). (3) The pediatric patients in the renal damage group had statistically significantly longer fever durations, higher blood EBV-DNA loads, and lower blood CD4+/CD8+ T lymphocyte ratios than those in the non-renal damage group.ConclusionIn pediatric patients, the incidence rate of acute EBV-induced renal damage is not low. The clinical manifestations are mostly hematuria or proteinuria, with an overall good prognosis, but occasionally severe renal damage such as acute renal failure. The possibility of secondary renal damage is high when pediatric patients with acute EBV have prolonged fever, high blood EBV-DNA loads, and decreased blood CD4+/CD8+ ratios.

Additional file 1: Supplementary Table1. Univariate analysis of gastrointestinalbleeding events. Supplementary Table2. Univariate analysis of death events.

Silicon is a beneficial element for plant growth, as well as for improving plant resistance to multiple biotic and abiotic stresses. Gummosis is a common harmful disease in peach and is induced by many factors. However, the effect of silicon on gummosis of peach has not been determined yet. In this study, we reported that application of silicon significantly reduced gummosis by regulating biosynthesis of ethylene and polyamines in peach. Ethylene promoted the development of gummosis by inducing the expression of genes encoding cell wall degrading enzymes. While application of different types of polyamines, including spermidine and spermine, dramatically inhibited the occurrence of gummosis. Moreover, polyamines inhibited the ethylene biosynthesis by down-regulating expression of ethylene biosynthetic gene PpACS1 (1-aminocyclopropane -1-carboxylic acid synthase), as well as the enzymatic activity of ACS. We further found that application of silicon significantly restricted the development of gummosis in peach. Exogenous silicon dramatically inhibited expression of PpACS1 and the enzymatic activity of its product to reduce ethylene biosynthesis. Simultaneously, the activity of S-adenosylmethionine decarboxylase, a key enzyme in ployamines biosynthesis, was increased by 9.85% under silicon treatment, resulting in elevated accumulation of polyamines. Thus, our data proved that application of silicon restricted gummosis development by activating ployamines biosynthesis and inhibiting ethylene synthesis in peach.

Visual perceptual decoding is one of the important and challenging topics in cognitive neuroscience. Building a mapping model between visual response signals and visual contents is the key point of decoding. Most previous studies used peak response signals to decode object categories. However, brain activities measured by functional magnetic resonance imaging are a dynamic process with time dependence, so peak signals cannot fully represent the whole process, which may affect the performance of decoding. Here, we propose a decoding model based on long short‐term memory (LSTM) network to decode five object categories from multitime response signals evoked by natural images. Experimental results show that the average decoding accuracy using the multitime (2–6 s) response signals is 0.540 from the five subjects, which is significantly higher than that using the peak ones (6 s; accuracy: 0.492; p, Visual perceptual decoding is one of the important and challenging topics in cognitive neuroscience. Building a mapping model between visual response signals and visual contents is the key point of decoding.

New high-resolution x-ray spectra of Mo39+, Mo40+, W43+, W44+ and W45+ have been carefully confirmed for the first time by use of the x-ray imaging crystal spectrometer (XCS) in Experimental Advanced Superconducting Tokamak (EAST) under various combined auxiliary heating plasmas conditions. Wavelength of these new x-ray spectra is ranged from 3.895 {\AA} to 3.986 {\AA}. When core electron temperature (Te0) reaches 6.0 keV, Mo39+ and Mo40+ lines of 3.9727, 3.9294 and 3.9480 {\AA} can be effectively detected on XCS for EAST; meanwhile, line-integrated brightness of these spectral lines of Mo39+ and Mo40+ is very considerable when electron temperature reaches 12.9 keV. Multi-components spectral lines for W43+, W44+ and W45+ have also been identified when Te0 reaches 6 keV. Parts of spectral lines, such as Zn-1, Cu-2, Cu-4a, Cu-4d and Cu-5 lines of tungsten, are first observed experimentally. When electron temperature reaches 12.9 keV, line-integrated intensity for part of these spectral lines of W43+, W44+ and W45+ are considerable. These experimental results and theoretical predictions from FAC and FLYCHK codes are in good general agreement. These new spectral lines, obtained on XCS for EAST, are vital for deeply uncovering the mechanisms of ion and electron thermal, high-Z impurity and momentum (anomalous) transport to achieve the advanced steady-state operation scenarios for ITER and CFETR.

Uplift modeling is a rapidly growing approach that utilizes causal inference and machine learning methods to directly estimate the heterogeneous treatment effects, which has been widely applied to various online marketplaces to assist large-scale decision-making in recent years. The existing popular models, like causal forest (CF), are limited to either discrete treatments or posing parametric assumptions on the outcome-treatment relationship that may suffer model misspecification. However, continuous treatments (e.g., price, duration) often arise in marketplaces. To alleviate these restrictions, we use a kernel-based doubly robust estimator to recover the non-parametric dose-response functions that can flexibly model continuous treatment effects. Moreover, we propose a generic distance-based splitting criterion to capture the heterogeneity for the continuous treatments. We call the proposed algorithm generalized causal forest (GCF) as it generalizes the use case of CF to a much broader setting. We show the effectiveness of GCF by deriving the asymptotic property of the estimator and comparing it to popular uplift modeling methods on both synthetic and real-world datasets. We implement GCF on Spark and successfully deploy it into a large-scale online pricing system at a leading ride-sharing company. Online A/B testing results further validate the superiority of GCF.

Additional file 1: Table S1. Mapping statistics of the RNA-Seq data for three replicates in each treatment. Table S2. DEGs involved in ROS scavenging. Table S3. DEGs involved in hormone signal transduction. Table S4. DEGs involved in amino acids metabolism. Table S5. DEGs involved in starch and sucrose metabolism.

Estimating long-term causal effects based on short-term surrogates is a significant but challenging problem in many real-world applications, e.g., marketing and medicine. Despite its success in certain domains, most existing methods estimate causal effects in an idealistic and simplistic way - ignoring the causal structure among short-term outcomes and treating all of them as surrogates. However, such methods cannot be well applied to real-world scenarios, in which the partially observed surrogates are mixed with their proxies among short-term outcomes. To this end, we develop our flexible method, Laser, to estimate long-term causal effects in the more realistic situation that the surrogates are observed or have observed proxies.Given the indistinguishability between the surrogates and proxies, we utilize identifiable variational auto-encoder (iVAE) to recover the whole valid surrogates on all the surrogates candidates without the need of distinguishing the observed surrogates or the proxies of latent surrogates. With the help of the recovered surrogates, we further devise an unbiased estimation of long-term causal effects. Extensive experimental results on the real-world and semi-synthetic datasets demonstrate the effectiveness of our proposed method.

The four-wheeled Mecanum robot is widely used in various industries due to its maneuverability and strong load capacity, which is suitable for performing precise transportation tasks in a narrow environment, but while the Mecanum wheel robot has mobility, it also consumes more energy than ordinary robots. The power consumed by the Mecanum wheel mobile robot varies enormously depending on their operating regimes and environments. Therefore, only knowing the working environment of the robot and the accurate power consumption model can we accurately predict the power consumption of the robot. In order to increase the appli-cable scenarios of energy consumption modeling for Mecanum wheel robots and improve the accuracy of energy consumption modeling, this paper focuses on various factors that affect the energy consumption of the Mecanum wheel robot, such as motor temperature, terrain, the center of gravity position, etc. The model is derived from the kinematic and kinetic model combined with electrical engineering and energy flow principles. The model has been simulated in MATLAB and experimentally validated with the four-wheeled Mecanum robot platform in our lab. Experimental results show that the model is 90% accurate. The results of energy consumption modeling can help robots to save energy by helping them to perform rational path planning and task planning.

In wind turbine planetary gearboxes, the sun gears are generally designed to float in the radial direction to achieve the uniform load distribution among different planet gears, but will lead to gear mesh errors and cause complicated vibration signals on the contrary. The floating sun gear is misdiagnosed as a distributed defect easily. Additionally, the floating sun gear's rotating motion and excitation force are too disorderly to be characterized by mathematical or empirical formulas. In the paper, a set of rigid-flexible coupling dynamics models of planetary gear train are built to research vibration characteristics of the floating sun gear under different conditions. Depend on the model-based vibration analysis, the rotating motion of floating sun gear is revealed well, which can be characterized by its frequency features, meanwhile mechanisms of modulation sidebands indicating different kinds of defects are deduced clearly. The experimental data keep good consistency with the simulation signals, which verifies the validity of the proposed well. Vibration feature indicators are obtained to distinguish fault signals and diagnose the distributed or localized defect of floating sun gear effectively, which is helpful to avoid the misdiagnosis of floating sun gear.

Long-time service and intricate work situation of gearbox make it liable to fault. The vibration signal of fault gear generally includes amplitude-modulation (AM) and phase-modulation (PM) components, which are the manifestation of fault and have strong connection with fault diagnosis. The corresponding relationships of AM and PM with gear fault type still lack of clarity. This paper proposes an accurate separation method of AM and PM signal, which contains squared amplitude demodulation and phase demodulation based on Bessel function of the first kind. Discrete spectrum correction technique is employed to correct modulation frequency and amplitudes in amplitude spectrum, which are utilized to establish system of nonlinear equations of AM and PM parameters. Trust-region reflective least square algorithm is then applied to solve these parameters and extract AM and PM components in sequence. The accuracy of this method is proved by various simulation signal. Additionally, simulation signals with different SRNs are employed to verify the anti-noise performance of the proposed method, which is further compared to Hilbert demodulation and energy-operator-based demodulation. Comparison results manifest the superiority of the proposed method in anti-noise performance. Experimental analyses confirm the effectiveness of this method and show the visible differences of separated PM components under different gear fault conditions, which can be used as an accordance of broken-tooth fault diagnosis. The relationship of the size of broken-tooth and modulation intensity is researched by the proposed method, which indicates that more serious broken-tooth degree behaves stronger modulation. A novel diagnosis method for gear broken-tooth fault is finally generated.

Graph neural networks have become an important tool for modeling structured data. In many real-world systems, intricate hidden information may exist, e.g., heterogeneity in nodes/edges, static node/edge attributes, and spatiotemporal node/edge features. However, most existing methods only take part of the information into consideration. In this paper, we present the Co-evolved Meta Graph Neural Network (CoMGNN), which applies meta graph attention to heterogeneous graphs with co-evolution of node and edge states. We further propose a spatiotemporal adaption of CoMGNN (ST-CoMGNN) for modeling spatiotemporal patterns on nodes and edges. We conduct experiments on two large-scale real-world datasets. Experimental results show that our models significantly outperform the state-of-the-art methods, demonstrating the effectiveness of encoding diverse information from different aspects., Comment: 11pages, 4figures

Water-jet laser processing is an internationally advanced technique, which combines the advantages of laser processing with water jet cutting. In the study, the experiment of water-jet laser dicing are conducted with ns pulsed laser of 1064 nm irradiating, and Smooth Particle Hydrodynamic (SPH) technique by AUTODYN software was modeled to research the fluid dynamics of water and melt when water jet impacting molten material. The silicon surface morphology of the irradiated spots has an appearance as one can see in porous formation. The surface morphology exhibits a large number of cavities which indicates as bubble nucleation sites. The observed surface morphology shows that the explosive melt expulsion could be a dominant process for the laser ablating silicon in liquids with nanosecond pulse laser of 1064 nm irradiating. Self-focusing phenomenon was found and its causes are analyzed. Smooth Particle Hydrodynamic (SPH) modeling technique was employed to understand the effect of water and water-jet on debris removal during water-jet laser machining.

Network embedding is an effective way to solve the network analytics problems such as node classification, link prediction, etc. It represents network elements using low dimensional vectors such that the graph structural information and properties are maximumly preserved. Many prior works focused on embeddings for networks with the same type of edges or vertices, while some works tried to generate embeddings for heterogeneous network using mechanisms like specially designed meta paths. In this paper, we propose two novel algorithms, GHINE (General Heterogeneous Information Network Embedding) and AHINE (Adaptive Heterogeneous Information Network Embedding), to compute distributed representations for elements in heterogeneous networks. Specially, AHINE uses an adaptive deep model to learn network embeddings that maximizes the likelihood of preserving the relationship chains between non-adjacent nodes. We apply our embeddings to a large network of points of interest (POIs) and achieve superior accuracy on some prediction problems on a ride-hailing platform. In addition, we show that AHINE outperforms state-of-the-art methods on a set of learning tasks on public datasets, including node labelling and similarity ranking in bibliographic networks.

Deep neural networks have been widely used in text classification. However, it is hard to interpret the neural models due to the complicate mechanisms. In this work, we study the interpretability of a variant of the typical text classification model which is based on convolutional operation and max-pooling layer. Two mechanisms: convolution attribution and n-gram feature analysis are proposed to analyse the process procedure for the CNN model. The interpretability of the model is reflected by providing posterior interpretation for neural network predictions. Besides, a multi-sentence strategy is proposed to enable the model to beused in multi-sentence situation without loss of performance and interpret ability. We evaluate the performance of the model on several classification tasks and justify the interpretable performance with some case studies.

Vibration responses of faulty gear contain modulation components that are commonly used as the indicators to detect the fault. The modulation mechanism has not been revealed clearly, especially the sideband distribution of amplitude modulation and frequency modulation. Aiming at the vibration modulation mechanism of fault gear, the gear meshing stiffness with frequency modulation components is deduced considering the actual speed fluctuation, as well as its influence on vibration responses. A series of phenomenon models of gear pair are built to research the sideband distribution features of vibration responses related to different types of gear faults. Both the steady-type and impact-type gear faults are proved to generate asymmetric amplitude-frequency modulation sidebands around harmonics of the meshing frequency. The marked difference lies in that the steady-type fault features distribute within a finite band while the impact-type fault features cover the entire frequency range and induce spurious resonance peaks. Sidebands with both amplitude and frequency modulations are wider than those with only amplitude modulation, and the product of two groups of frequency modulation components is proved to bring in amplitude modulation components. The phenomenon models of gear vibration responses contribute a deeper understanding of modulation mechanism of faulty spur gear, and the obtained sideband distribution features of amplitude-frequency modulation are an effective aid for gear fault diagnose.

Montmorillonite calcium (MMT-Ca) was functionalized with cetyltrimethylammonium bromide (CTAB) via cationic exchange effects. Compared with MMT-Ca, the resulting CTAB functionalized MMT-Ca (CTAB/MMT-Ca) greatly increased the oxidation peak current of sunset yellow, indicative of strong signal enhancement effects. The oxidation mechanism was studied, and one electron was transferred during the oxidation of sunset yellow. The influences of pH value, mass ratio of CTAB to MMT-Ca, amount of CTAB/MMT-Ca, and accumulation time were studied on the oxidation signal of sunset yellow. As a result, a highly-sensitive, rapid and simple electrochemical method was newly developed for the determination of sunset yellow. The linear ranger was from 2.5 to 200 nM, and the detection limit was as low as 0.71 nM after 1-min accumulation. This method was applied in soft drink samples, and the detected results consisted with the values that obtained by high-performance liquid chromatography.

Background: SET and MYND domain-containing protein 3 (SMYD3) is a histone methyltransferases and it promotes progression of many kinds of cancers including lung cancer, ovarian cancer and gastric cancer. In colorectal cancer (CRC), SMYD3 is proved to stimulate the proliferation of cancer cells, but the clinical significance of SMYD3 in CRC has not been elucidated. Methods: In our study, we detected the expression of SMYD3 in CRC samples in TNM stage I-III with immunohistochemistry. The correlation between the expression of SMYD3 and the clinicopathological factors was analyzed with Chi-square test. The survival curve was displayed by Kaplan-Meier test and the statistical difference of subgroups was analyzed with log-rank test. Independent prognostic factors were identified by the Cox proportional hazards regression model. Results: The percentage of high SMYD3 expression and low expression accounts for 47.98% and 52.02% respectively. High expression of SMYD3 was significantly associated with advance T stage (P=0.006) and lower survival rates (P=0.010), and it could be identified as an independent prognostic factor indicating unfavorable prognosis of patients with CRC (P=0.032, HR=1.98, 95% CI=1.06-3.70). Conclusions: SMYD3 high-expression is a high risk for poorer prognosis of CRC in TNM stage I-III. Our findings suggested that detecting SMYD3 may help stratify patients by risk more preciously and help make the individual treatment strategy.

Serological biomarkers may be an option for early detection of colorectal cancer (CRC). The present study assessed eight cancer-associated protein biomarkers in plasma from subjects undergoing first time ever colonoscopy due to symptoms attributable to colorectal neoplasia. Plasma AFP, CA19-9, CEA, hs-CRP, CyFra21-1, Ferritin, Galectin-3 and TIMP-1 were determined in EDTA-plasma using the Abbott ARCHITECT® automated immunoassay platform. Primary endpoints were detection of (i) CRC and high-risk adenoma and (ii) CRC. Logistic regression was performed. Final reduced models were constructed selecting the four biomarkers with the highest likelihood scores. Subjects (N = 4,698) were consecutively included during 2010-2012. Colonoscopy detected 512 CRC patients, 319 colonic cancer and 193 rectal cancer. Extra colonic malignancies were detected in 177 patients, 689 had adenomas of which 399 were high-risk, 1,342 had nonneoplastic bowell disease and 1,978 subjects had 'clean' colorectum. Univariable analysis demonstrated that all biomarkers were statistically significant. Multivariate logistic regression demonstrated that the blood-based biomarkers in combination significantly predicted the endpoints. The reduced model resulted in the selection of CEA, hs-CRP, CyFra21-1 and Ferritin for the two endpoints; AUCs were 0.76 and 0.84, respectively. The postive predictive value at 90% sensitivity was 25% for endpoint 1 and the negative predictive value was 93%. For endpoint 2, the postive predictive value was 18% and the negative predictive value was 97%. Combinations of serological protein biomarkers provided a significant identification of subjects with high risk of the presence of colorectal neoplasia. The present set of biomarkers could become important adjunct in early detection of CRC.

Samples were collected from Great Xing′an Mountains during 2004 to 2007.Six taxa of Aulonoraphidinales were identified as the newly recorded species in China.They are:Hantzschia calcifuga Reichardt & Lange-Bertalot, Nitzschia homburgiensis Lange-Bertalot, Nitzschia nana Grunow, Nitzschia terrestris (Petersen) Hustedt, Stenopterobia anceps (Lewis) Brébisson, Stenopterobia delicatissima (Lewis) Brébisson ex Van Heurck.The morphological features and habitat distribute pattern of these taxa were reported in this paper.

The reflection coefficients from a gold-plated coaxial line probe submerged in different electrolyte aqueous solutions are measured under different microwave powers and constant temperature. Measurements were performed at 915 MHz. Furthermore, a GA-based inverse calculation technique was formulated and used to determine the effective conductivity of the solution from the measured reflection coefficients. A new phenomenon was observed: the effective conductivity of electrolyte aqueous solutions can be directly influenced by microwave power. Any thermal effect was excluded using multiphysics calculation and temperature measurement during the experiment for sodium chloride aqueous solution. Therefore, it was concluded that nonthermal effect of sodium chloride aqueous solution under microwave radiation exists. © 2011 Wiley Periodicals, Inc. Microwave Opt Technol Lett 54:222–225, 2012; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.26500

Microwave has been found as an efficient heating method in chemical industry. However, in present days the interaction between microwave and chemical reactions has not been deeply understood, which restricts a wider application of high power microwave in chemical industry. In this paper, the key problems of interaction between microwave and chemical reaction are investigated, such as complex effective permittivity of chemical reaction, simulation of microwave heating on chemical reaction and non-thermal effect of microwave, which will enhance further knowledge of the mechanism of interaction between microwave and chemical reaction. Moreover, such an analysis is beneficial for handling with difficulties in application of microwave chemical industry.

The purpose of the study is to investigate the effect of ent-11α-hydroxy-15-oxo-kaur-16-en-19-oic-acid (5F) on the model of induced A/J mice lung cancer in A/J mice. The expressions of tumor-related molecules including P65 and Bcl-2 at protein level were examined using the immunohistochemical method (IHC). Side effects of 5F were also monitored. The results indicated that 5F significantly suppressed the development of B[a]P and NNK-induced lung cancer in vivo by facilitating cell apoptosis with minimal side effects. Compared to the expressions of P65 and Bcl-2 in model group, the levels were strongly attenuated both in blank and 5F injection groups. Moreover, P65 and Bcl-2 levels varied among different groups receiving 5F treatment. The expressions of P65 and Bcl-2 were much lower in groups receiving high-concentration 5F treatment than those with low-concentration 5F injection. Findings revealed that 5F inhibited the pathogenesis of lung cancer through accelerating apoptosis in a dose-dependent manner.

Through careful research and analysis on wireless sensor network (WSN), this paper confirms the important function of MAC protocol on wireless network communication. Moreover, through OPNET simulation software, this paper simulates different working scenes, and carefully researches MAC layer in IEEE 802.15.4 protocol. The data comparison result shows that GTS mechanism has the lowest energy consumption and it can delay the network lifetime in actual work. Keywords-wireless sensor network (WSN); low power consumption; MAC protocol; energy saving.

In this study, various nanoemulsion formulations were prepared to encapsulate non-polar beta-carotene and partly polar flavor molecule citral. For the encapsulation of beta-carotene, the nanoemulsion core material was a mixture of both solid lipid (palm kernel fat) and liquid oil (medium chain triglyceride, MCT). Aqueous nanoemulsion dispersions were obtained by the combination of high speed and high pressure homogenization processes and the solid nanoemulsion powders were also obtained by lyophilization using sucrose as the cryoprotectant. For the aqueous dispersions, the formulation using pure palm kernel fat as the lipid phase was the best one to protect beta-carotene from degradation. For the freeze-dried samples, the incorporation of liquid MCT oil is necessary to disturb solid lipid crystallization to protect beta-carotene. The in vitro digestion experiments were performed to evaluate the bioaccessibility of beta-carotene in palm kernel fat nanoemulsion and MCT nanoemulsion; the results showed that the bioaccessibility of beta-carotene was greatly improved after encapsulation. The palm kernel fat had better performance than the MCT to release beta-carotene from the nanoemulsion formulations. For the encapsulation of citral, two strategies were developed to improve citral stability at acidic condition (pH = 3.0). The first strategy was to incorporate six different natural antioxidants (black tea extract, ascorbic acid, naringenin, tangeretin, beta-carotene and tanshinone) with citral together in the palm kernel fat nanoemulsions. The second strategy was to construct multilayer nanoemulsions to encapsulate citral. The multilayer emulsions were prepared by the layer-by-layer deposition technique between oppositely charged emulsion droplets and two polymer coatings: chitosan (CS) and ε-polylysine (EPL). The stability of citral as well as the production of the off-flavor compounds was analyzed by solid phase microextraction gas chromatography (SPME-GC). The results suggested that encapsulation of citral in combine with the appropriate antioxidants (beta-carotene, tanshinone and black tea extract) could greatly enhance citral’s chemical stability during storage; and the additional cationic chitosan interfacial layer was also effective to improve the stability of citral.

Traditional control system usually uses a single expert system for fault-diagnosis, which is unitary and unable to deal with problems in the complicated and flexible network environment. In this paper, expert system and neural network system are combined for fault detection and diagnosis, which can greatly increase the efficiency and accuracy of network fault diagnosis. The networked control system discussed in the paper have several indices for fault diagnosis, which can be processed as input of BP neural network, and the training result proved to be good.