Search

Through the simulation and calculation of object Petri net modeling and simulation environment (OPMSE) for the emission mass concentrations of COD， BOD5 and NH3-N in waste water from paper-making industry， the range of COD， BOD5 and NH3-N mass concentrations in typical paper-making industry were inquiried and investigated in Qinghe basin. The results show that when the confidence level is 99%， the confidence interval of COD is (34.09， 41.84)， the confidence interval of BOD5 is (6.65， 8.40)， and the confidence interval of NH3-N is (6.28， 7.34). The mass concentration of the optimum effluent is ρ(COD)=12. 79mg/L， ρ(BOD5)=2.62mg/L， ρ(NH3-N)=3. 33mg/L， while the mass concentrations of the worst effluent are ρ(COD)=70.47mg/L， ρ(BOD5)=14.51mg/L， ρ(NH3-N)=10.22mg/L. Then making a comparison between the emission standards and simulation results are got. The direct emission limits of the paper-making industry are ρ(COD)=45mg/L， ρ(BOD5)=9mg/L， ρ(NH3-N)=8mg/L. [ABSTRACT FROM AUTHOR]

According to the collected fault information of a domestic NC machine tool, the subsystem is divided, and the reliability allocation method is improved according to the NC machine tool correlation model to allocate the target value. The membership degree set of influencing factors is established using the analytic hierarchy process （AHP), and the centrality influencing factors of fault-related data are determined using the DEMATEL decision laboratory analysis method. The membership function set is determined by combining maintainability, maintenance time, failure downtime, failure times, and complexity. Then the reliability allocation factor of the NC machine tool is calculated. The impact factor is introduced into the ARINS allocation method to improve the method so that the improved method is suitable for the system with subsystems connected in series and fault correlation. Numerical examples show that the proposed method can reduce the failure time requirement of the subsystem compared with the traditional ARINS method. At the same time, to verify the rationality of the distribution results in this paper, the Monte Carlo simulation method is used to predict the reliability of the target machine tool based on the distribution results, and the calculation results prove the feasibility of this method. [ABSTRACT FROM AUTHOR]

During sintering the vanadium titanomagnetite, TiO2 competes with Fe2O3 for CaO, which inhibits the formation of calcium ferrite （CxF） and affects the sinter quality. In this paper, the diffusion reaction of CaO-Fe2O3-TiO2 system is intuitively studied by preparing CxF/TiO2 diffusion couple. Electron probe and X-ray diffractometer are used to analyze and characterize the products at different positions of the reaction interface. The reaction characteristics of CxF/TiO2 interface are studied at the diffusion temperature of 900~1050 ℃ and the time of 1~4 h. The effects of temperature and time on the types, distribution and morphology of the generated phases are discussed. The results show that the main phases are CxF, CaO·Fe2O3 （CF）, Fe2O3, CaTiO3 and TiO2 from the CxF- to TiO2-layer, among which perovskite （CaTiO3 ） is the main product. The thickness of CaTiO3 increases from 8. 1 μm to 90. 2 μm with the temperature increasing from 900 ℃ to 1 050 ℃； it increases from 47. 4 μm to 121. 4 μm with the time increasing from 1 h to 4 h. Meanwhile, the diffusion thickness of CaTiO3 has a good linear relationship with the square root of diffusion time, which indicates that the formation of CaTiO3 is controlled by diffusion process. Furthermore, the formation process of CaTiO3 in CaO-Fe2O3-TiO2 system is explained by vacancy-mediated diffusion mechanism. [ABSTRACT FROM AUTHOR]

The permeability-based hydraulic fracture-level set method(PHF-LSM)is a smeared fracture model based on Biot consolidation theory. The model simulates the fracture development process by weakening the fracture and rock material properties in the damaged area， so the geometric characteristics of hydraulic fractures cannot be given in the solution process. According to the average effective stress field distribution during hydraulic fracture propagation， the equivalent path and equivalent height of hydraulic fracture by PHF-LSM method are established in this paper. According to the displacement field around the equivalent propagation path， the equivalent opening of hydraulic fractures is calculated， and the effectiveness of the proposed method is verified by comparing with KGD theoretical model. At the same time， the dynamic development characteristics of equivalent geometric characteristics for fractures in both homogeneous and heterogeneous rock are calculated. The results demonstrate that the established equivalent calculation method compensates for the deficiency of PHF-LSM by allowing for the determination of geometric characteristics of hydraulic fractures. [ABSTRACT FROM AUTHOR]

Shield load is the main performance indicator of the shield, accurate load prediction is significant to ensure the safety and efficiency of the shield and the stability of the surrounding environment. Recognizing the limitations of the traditional prediction methods, this paper proposes a hybrid model (CBM), combining convolutional neural network (CNN), bi-directional long short-term memory (BiLSTM) and attention mechanism, to predict the shield load accurately based on the high-dimensional feature and time series characteristic of the data. The proposed model not only can extract the high-dimensional features and time series characteristics of the data, but also can highlight the importance of high-dimensional features and important time node information. The experiment results show that compared with the existing models, the proposed model achieves a higher prediction performance, the prediction accuracy of the thrust and torque is 94.2% and 96.2%. [ABSTRACT FROM AUTHOR]

The research on macroscopic rate-dependence of concrete has achieved very rich results, and its meso structural and material parameters significantly affect the macroscopic mechanical properties of concrete. Therefore, studying the dynamic properties of concrete at the meso-scale is an important way to reveal the macroscopic rate-dependence of concrete. In this paper, the influence of strain rate was introduced to modify the interfacial cohesion constitutive model, and the uniaxial tensile failure mode and mechanical properties of concrete with different aggregate content and shapes were studied under various loading rates from the mesoscale. The results show that the distribution of failure cracks becomes increasingly uniform with the increase of loading rate. The increment in tensile strength of concrete exhibits a linear relationship with the logarithm of strain rate. The tensile strength of concrete decreases linearly with an increase in aggregate content, while the aggregate shape has little effect on it. [ABSTRACT FROM AUTHOR]

Aiming at the difficult exploration problems of traditional Skill discovery algorithms such as SNN-HRL(stochastic neural networks for hierarchical reinforcement learning), this paper proposes a hierarchical reinforcement learning algorithm that integrates multiple exploration strategies (MES) based on SNN-HRL algorithm. The proposed algorithm improves the traditional hierarchical structure, including three layers: exploration trajectory layer, learning trajectory layer, and path planning layer. In the exploration trajectory layer, the trained agent can explore as many unknown environments as possible to provide sufficient environmental state information for the subsequent training process. In the learning trajectory layer, the training results of the exploration trajectory layer are used as "priori knowledge" for the training to improve the training efficiency. In the path planning layer, skill that agent has learned are used to complete the path planning task. By comparing the performance of the MES-HRL and SNN-HRL algorithms in different environments, the simulation results show that MES-HRL algorithm solves the exploration problem of the traditional version of the algorithm and has better path planning capabilities. [ABSTRACT FROM AUTHOR]

In view of the easy steering instability of vehicles running sideways, this paper considers the variation of tire cornering stiffness to avoid saturation of tire lateral force and improve driving safety and constructs a vehicle stability control method. The front and rear axle tire sideslip angle segmented fitting method is used to establish a tire cornering stiffness fitting model, and then the fitted cornering stiffness is introduced into the vehicle dynamics model to accurately describe the current dynamic performance of the vehicle. In order to avoid the steering instability caused by the saturation of the tire lateral force, this paper proposes a vehicle stability control method based on the model predictive control (MPC) algorithm that considers the constraints of the front and rear axle tire sideslip angles to optimize the vehicle’s steering performance. Simulation results show that the proposed vehicle stability control method can suppress the tire sideslip angle of the front axles within a certain range, while taking into account the changes in the cornering stiffness, thereby avoiding the occurrence of vehicle sideslip and improving the stability performance of the vehicle. [ABSTRACT FROM AUTHOR]

The series of HY-2 satellites have accumulated a large amount of data, and the improvement of the resolution of the along orbit geoid of altimetry data is closely related to the refinement of the ocean gravity field model. This paper utilizes self-spectrum analysis, cross spectrum analysis, and coherence function calculation to estimate along orbit geoid resolution of satellite altimetry data. Spatially similar trajectory sequences of HY-2B and SARAL/AltiKa, as well as HY-2C and Jason-2, were selected to carry out the experiment. The results show that the average resolution of HY-2C is 19.15 km, slightly better than HY-2B and Jason-2, but slightly lower than the SARAL/AlitKa Ka-band altimetry data with higher pulse repetition frequency. In addition, the repeated period collinear processing can significantly improve the resolution of along-track geoid by effectively suppressing noise. Under the condition of 5, 10 and 20 periods collinear processing, the resolution of HY-2B along orbit is improved by 19.26%, 38.56% and 46.69%, respectively. Therefore, when HY-2A, CryoSat-2 and other altimetry missions provide the observation sequence of geodetic missions with multi-period and repeated observations, the necessary collinear processing will bring more efficient data fusion for the refinement of marine gravity field model. [ABSTRACT FROM AUTHOR]

According to the characteristics of irregular random charge and discharge of electric vehicles and the requirements of on-line detection, it is difficult to ensure the accuracy of off-line experimental data analysis methods due to battery consistency problems. In this paper, an on-line closed-loop correction SOH (state of health） estimation architecture based on the idea of unscented Kalman filter (UKF) is proposed, which is based on the off-line SOH external indicator function. The advantage of this method is that it can quickly estimate the high-precision SOH value in the random discharge process and the algorithm complexity is relatively reduced. It is easy to implement in practical engineering and the proposed method has better robustness. Through verification, it can be proved that the SOH estimation method proposed in this paper has better practicability and higher estimation accuracy. [ABSTRACT FROM AUTHOR]

Real-time target detection in traffic scenarios is the prerequisite of electronic monitoring, automatic driving, and other functions. In view of the low detection efficiency of existing target detection algorithms and the low accuracy of most light target detection algorithms, which are easy to obtain wrong or insufficient target detection, this paper adopts the improved YOLOv5 target detection algorithm for model training, and the pseudo-label strategy for training process optimization. Then, the KITTI traffic target dataset tags are merged into three categories for model training and testing. Through the experimental comparison, the improved YOLOv5 model in this paper achieves 92.5% mAP in all categories, which is 3% higher than the original YOLOv5 training model. Finally, the three categories of the trained models are deployed on the Jetson Nano embedded platform for inference testing, and TensorRT is used to accelerate inference. The average inference time per frame of image is 77 ms, which meets the goal of real-time detection. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the classic puncture path planning algorithm does not consider the area around the path when quantifying the path, new constraints condition are proposed to make up for the lack of quantification of the information around the path. A strict constraint condition was proposed based on the blood vessel position information (the surrounding area avoids the blood vessel), and based on bone density, blood vessel density, and diameter information, three soft constraints (bone density, blood vessel density, and blood vessel risk) were proposed, and the surrounding information was added to the quantification of the path to improve the safety of the puncture path. In order to adapt to the specificity of patients, a soft constraint optimization degree scoring algorithm is proposed, and the weight is set according to the optimization degree of soft constraints, and the puncture path corresponding to the maximum optimization degree is taken as the optimal puncture path. In order to verify the effectiveness of the algorithm, experiments were carried out on the public dataset 3D-IRCADb. The experimental results show that the algorithm proposed in this paper can quickly calculate the optimal puncture path that meets the clinical needs. [ABSTRACT FROM AUTHOR]

In order to systematically study the influence of the introduction of hydroxyethyl on the performance of quaternary ammonium salt collectors, flotation test, contact angle test, toxicity test, degradation test, surface tension test, Zeta potential test, molecular dynamics analysis and other methods were adopted in this paper. The performance differences of dodecyl dihydroxyethyl methyl ammonium bromide (BHMDB) and dodecyl trimethyl ammonium bromide (DTAB) were studied, and the influence mechanism of hydroxyethyl on the performance of collector quaternary ammonium salts was analyzed. Compared with DTAB, BHMDB has better collection capacity, flotation selectivity, pH adaptability and hydrophobicity. The introduction of hydroxyethyl reduces the toxicity and critical micelle concentration of the solution, but makes the degradation worse. Through the analysis of the mechanism of the collector, it can be seen that the introduction of hydroxyethyl group strengthens the hydrogen bond between the agent and the mineral surface, increases the cross-sectional area of the polar group of the agent, and makes it more selective. [ABSTRACT FROM AUTHOR]

The pore pressure response of a two-dimensional seepage field in an isotropic soil layer under the condition of periodic fluctuation of groundwater level is studied analytically. The soil around the pit is divided into four regular regions, and the expressions of the series solution form of the pore pressure response in each region are obtained by applying the superposition principle and the method of separation of variables, and the explicit analytical solution of the pore pressure of the seepage field around the pit is solved by combining the continuous conditions between the regions. The results of the analytical solution are compared with the results of numerical software and semi-analytical solutions to verify the correctness of the analytical solution method in this paper. Based on this solution, the influence of the variation of engineering parameters such as water level inside and outside the pit on the pore pressure response distribution and phase lag is analyzed. The results show that the pore pressure response and phase lag are influenced by the engineering parameters of the pit, and the influence on the far-field pore pressure response and the phase lag inside the pit is more obvious. [ABSTRACT FROM AUTHOR]

As the most representative signal of human emotion, EEG signal is becoming the mainstream signal source of emotion recognition. Transfer learning can overcome the problem of distribution difference between physiological signal source domain and target domain. The traditional transfer learning will have a negative impact on the transfer effect due to the lack of the selection process of samples and features, resulting in a low recognition rate. In order to improve the migration effect, this paper optimizes the migrated data in two aspects: samples and characteristics. A case selection method based on like value and an automatic feature selection method based on particle swarm optimization are introduced. Using JDA, a transfer learning framework for emotion recognition is proposed. Finally, two transfer learning tasks are constructed on the SEED dataset for verification. The results show that the framework can effectively improve the transfer effect and improve the accuracy of cross domain emotion recognition. [ABSTRACT FROM AUTHOR]

In this paper, based on the concepts of mixed model and Gibbs energy balance model, a simple Gibbs energy balance model was established to simulate the ferrite-austenite transformation of Fe-C-Mn low carbon steel during the intercritical annealing at 780℃. The effects of Gibbs free energy, effective grain size and alloying distribution on the transformation were studied. The results show that the initial effective grain size and interfacial mobility greatly affected the kinetics of phase transformation, while they had little effect on the final volume fraction of the austenite. The dissipation energy caused by the Mn enrichment at the interface during phase transformation slowed down the transformation kinetics and reduced the final volume fraction of the austenite. It is found that the modelling results above are in good accordance with the experimental ones. [ABSTRACT FROM AUTHOR]

Red blood cell (RBC), undertaking the significant work of oxygen transport to maintain human life, could shuttle spindly capillaries by their own stretching and contractile properties due to their biconcave discoid shape and hyperelastic responses. In this paper, the coupled fluid-solid module in finite element software COMSOL was used to study the dynamic simulation of RBC when the three factors, including capillary width, plasma viscosity, and blood flow rate were considered. The results implied that the RBC could easily pass through capillary with hole size of 3 μm, and the aqueous shear stress was 4.5 times greater than that in the capillary with 6 μm hole size. Meanwhile, the plasma viscosity of 5.5 mPa·s induced parachute-like formation of RBC. Furthermore, biconcave structure in the center gradually disappeared and turned into bulge along the flow direction. With regard to the study on fluidic velocities in T-shaped and Y-shaped micro-channel, both results indicated that the asymmetric structure caused the falcate shape of RBC. In addition, the higher fluidic velocity in the other branch channel, the easier the convergence leaded to the disappearance of falcate shape and the rod posture lying flat flowing in the solution. [ABSTRACT FROM AUTHOR]

The paper proposes a robot zero calibration device and method based on spatial parameter clustering identification to overcome the shortcomings of traditional shaft pin and laser tracker calibration. The dial indicator and spatial analytic geometry are used to construct the zero calibration equation， which analyzes the robot’s theoretical post and posture values to obtain the zero-position training parameters. The clustering module identifies multiple sets of zero-position training parameters， and the optimal zero-position parameters of each joint can be solved. The experimental results show that spatial parameter clustering can improve the absolute accuracy by 72.9%， compared to the most commonly used shaft pin calibration method. Compared with the laser tracker calibration method with the highest accuracy， the time efficiency is improved by 87.5%. This method considers the calibration accuracy and efficiency and significantly improves the adaptability to the calibration environment. [ABSTRACT FROM AUTHOR]

Due to the huge volume， complex structure and end effect of wind power gear， it is difficult to realize the uniform heating of tooth profile and tooth width， which affects the final strengthening quality. In this paper， the average temperature， the maximum temperature difference and the relative temperature fluctuation rate are taken as the evaluation indexes of the heating effect. The temperature fields along the tooth profile and the tooth width direction of wind power gear in the scanning induction heating process are studied， and the phase transformation and hardening of the gear are analyzed. It is found that the temperature uniformity increases gradually in the direction of tooth width from top to bottom within a certain range， which is due to the drastic change of tooth structure thickness. To gears strengthened by induction hardening in steady-state positions， the depth of hardened layer in the direction of tooth profile is almost the same as the depth of macroscopic phase change layer， and the transition region is relatively narrow. The heating effect and strengthening result of gear scanning induction heating are expounded， which provides the research foundation for the wide application of high-performance steel materials in the field of wind power. [ABSTRACT FROM AUTHOR]

The optimization algorithm of concrete pump truck global power matching technology has poor solution quality, this paper proposed a condition adaptive global power matching strategy based on advanced particle swarm optimization. Firstly, based on the characteristic data of engine and hydraulic pump, a pumping system model on MWorks that integrated five major modules of hydraulic, mechanical, control, load and power is builted; Then, the advanced particle swarm optimization algorithm is used for global matching optimization and output the economic matching value of parameters under different operation requirements; Finally, a pumping system simulation platform is established to analyze the energy-saving effect of different power matching strategies under typical conditions. The results show that compared with the traditional strategy, strategy proposed saves fuel by 5.86%, 5.24% and 1.74% under light, medium and heavy operation, respectively. [ABSTRACT FROM AUTHOR]

In order to answer two questions about de Bruijn graph(DBG) in bioinformatics: ① For any k-mer, answer whether it is the vertex of DBG; ② For any vertex of DBG, answer its adjacency information(incoming edge and outgoing edge), an efficient DBG indexing method for large-scale read mapping is proposed. In this paper, the above two questions are transformed into the exact finding problem of k-mer and (k+1)-mer on non-repetitive multipath, and are solved by using FM-index. Firstly, a given reference sequence is compressed, which is the discovery of non-repetitive multipaths, thereby compressing the presence of large-scale repetitive (k+1)-mers in the sequence. Secondly, the DBG is indexed based on the non-repetitive multipath FM-index. The k-mer is searched whether it appears on the DBG, and if so, the direct predecessor and direct successor nodes of the k-mer are provided to improve the spatial-temporal efficiency. Finally, experiments are performed on the genomes of 62 E. coli strains. The experimental results show that the method proposed can efficiently index the DBG of multi-reference sequences. [ABSTRACT FROM AUTHOR]

Model counting is the number of models for a given proposition formula, which is a basic problem in the field of artificial intelligence. There are many exactly-one constraints in many practical problems such as Bayesian networks, bounded model detection, and accurate set coverage. A common processing method is to encode exactly-one constraints as CNF formulas, and then call the model counter to solve them. This method expands the scale of the proposition formula and easily leads to too long solution time. This paper respectively proposes the ECR algorithm that restores exactly-one constraints from the CNF formula and the ECP algorithm that handles exactlyone constraints. The ECR algorithm can significantly improve the solution efficiency of the C2D compiler. Based on the latest model counter ExactMC, this paper improves the model counter ECMC that can recognize and handle exactly-one constraints separately. The experimental results show that the time efficiency of ECMC is significantly improved compared to ExactMC. [ABSTRACT FROM AUTHOR]

Aiming at the precision loss problem of most low-complexity Root-MUSIC algorithms at present, a low-complexity Root-MUSIC algorithm with precision compensation ability is studied and proposed. The algorithm reconstructs the autocorrelation matrix with Toeplitz shape according to the first row of the approximate data observation matrix obtained by finite snapshots, so that the reconstructed autocorrelation matrix has Hermitian property. After decomposing the reconstructed autocorrelation matrix, the noise subspace is obtained, the noise subspace is flipped and split, a new root-finding polynomial is reconstructed, and then the DOA estimated value is obtained by the root-finding method. The algorithm proposed in this paper using Toeplitz matrix reconstruction and root polynomial reduction effectively improves the DOA estimation accuracy of the improved Root-MUSIC algorithm. And the time complexity of the improved algorithm is no higher than that of previous algorithms. Under different incident sources and sampling snapshots, the algorithm proposed in this paper also shows stronger robustness and stability. [ABSTRACT FROM AUTHOR]

Network representation learning can effectively solve the problem of data sparsity in recommendation. In this paper, LINE and DeepWalk in network representation learning were improved, and a hybrid recommendation algorithm was proposed to be applied to movie recommendation scene. The new algorithm generates three low dimensional feature vectors by learning user preference feature, user aversion feature and similar user feature. Three low dimensional feature vectors are linearly combined to form a user representation vector, and cosine similarity is used as the similarity index to recommend the movies associated with similar users to target users. Experimental results show that, compared with the suboptimal algorithm, the accuracy and Fl index of the proposed algorithm are improved by 12% and 7% respectively on MovieLens dataset, and 16% and 18% respectively on MovieTweetings dataset. The recommendation algorithm based on multi-dimensional feature representation learning proposed in this paper has significant advantages in movie recommendation scenes. [ABSTRACT FROM AUTHOR]

In this paper, frequency is regarded as a new characteristic parameter to analyze vibration features. Firstly, the principle of vibration signal feature extraction was proposed, and the characteristic frequency function was obtained through the vibration feature extraction test of quick-point grinding. Then, the influence of different levels of technological parameters on grinding vibration under the machining or idle condition was analyzed. And the variation law of characteristic frequency was analyzed by comparing the contact and energy transfer relationship between the grinding wheel and workpiece. The results showed that the machining characteristic frequency is always smaller than the idle and the relative deviation of characteristic frequency decreases with the increase of the grinding wheel ' s linear velocity, and increases with the increase of grinding depth and feed velocity. At the same time, the influence weight of each technological parameter on the characteristic frequency was compared, and the idea of improving the machining efficiency was put forward. [ABSTRACT FROM AUTHOR]

Accurate segmentation of brain tissue in MR images is a key step in clinical diagnosis, surgical planning and adjuvant treatment. Deep-learning shows great potential in various image segmentation tasks, and existing models do not have an effective way to summarize the relationship between long-distance pixels. In the network decoding stage, the features of different levels cannot be well integrated, resulting in the inability to accurately locate. To overcome the above problems, this paper proposes a brain MR image segmentation method based on spatial self-attention mechanism and depth feature reconstruction, and constructs a 2D model that can fuse 3D information, which can quickly and accurately perform dense prediction on 3D structural images. The proposed method is fully experimented on MRBrainS13 data sets and IBSR data sets, and the results show that the model outperforms the current 2D model in 3D multimodal and unimodal brain MR image segmentation, with less computing and inference time compared to the 3D model, whereas the performance is very close. [ABSTRACT FROM AUTHOR]

Gear fault detection based on vibration analysis has been proven to be effective in fault identification. However， the extraction and identification of vibration signals characterizing early wear have not been solved well. This paper proposes a method for early wear diagnosis of gears， combining variational mode decomposition (VMD) based on spectrum correlation analysis with kernel support vector machine (SVM). For weak gear vibration signals that can characterize early wear， the modal numbers are initialized by an approximate complete reconstruction criterion. Meanwhile， the frequency corresponding to the maximum value of the signal power spectral density is used to initialize the center frequency of the VMD method. It is used to effectively extract gear wear information from gear vibration signals and then be combined with kernel support vector machines for early wear diagnosis of gears. The experimental results show that the proposed method can effectively overcome the problem that the modal numbers cannot be preset with large background noise， be with better robustness to noisy situations， and achieve a diagnostic accuracy of 94.4%， which provides a solution for early wear detection of gears. [ABSTRACT FROM AUTHOR]

Superheat is an important indicator to reflect the current production efficiency of aluminium electrolytic cells. Due to the difficulty of superheat online real-time measurement， this paper proposes a superheat identification method based on residual convolution self-attention neural network (RCSANN). As the production data in aluminium electrolysis process is time series data and featured with multi-source heterogeneous characteristics， the isomorphic representation method is designed for heterogeneous data. On this basis， the RCSANN superheat model is proposed to extract the global and local features of the isomorphic time series data. Aiming at the problem of few labels and uneven category distribution of superheat data， the unsupervised pre-training method based on auto-encoder and the weighted cross-entropy loss function are used to improve the performance of the superheat identification task. The validity of the proposed method is verified by simulation and comparison experiments on the benchmark dataset. Then， experiments are carried out on the dataset of superheat in aluminium electrolysis with only a few unbalanced labels. The results show that not only the accuracy of superheat identification is improved compared with other existing models， but also the generalization ability can be guaranteed under few training labeled-samples. [ABSTRACT FROM AUTHOR]

In this paper, sliding mode control is studied for a class of fractional-order singular systems with external disturbances, and an improved exponential reaching law is proposed to eliminate chattering in theory. The integral sliding surface is used to eliminate the approaching phase of sliding mode movement. Kronecker product and LMI method are used to design the gain matrix in order to stabilize the sliding mode equation in both cases: 0<α<1 and 1<α<2. In the design of sliding mode controller, the performance of exponential reaching law is improved, and the sign function is replaced by the designed continuous function, so that when the state approaches the sliding mode, the smooth transition can be achieved with the sliding mode. Finally, the simulation experiments of sliding mode control are established by Simulink to verify the effectiveness of the algorithm in both cases: 0<α<1 and 1<α<2. [ABSTRACT FROM AUTHOR]

Water in the external environment of the textile reinforced concrete(TRC)migrates along the direction of the internal directional fiber bundles, which causes the degradation of the impermeability of the internal matrix of the textile reinforced concrete. This paper studies the effects of the water-cement ratios, the textile sizes, and the fiber bundle Tex content in concrete matrix on the impermeability of TRC both in macro and micro scale. Meanwhile, the roughness of concrete was evaluated based on fractal dimension through nuclear magnetic resonance test. The results show that the impermeability of TRC decreases with the decrease of the mesh size of the textile, the increase of the Tex content and the increase of the water-cement ratio. A TRC seepage prediction model was also established based on the dimensional analysis method and permeability test, which can be used to describe the impermeability performance of TRC. [ABSTRACT FROM AUTHOR]

In this paper, a coal mine is used as the research region to study the problems caused by deep mining, such as rock burst, large deformation and failure of conventional bolt/cable. Based on the large deformation failure mechanism of high in-situ stress soft rock, the FLAC3 D-PFC3 D coupling modeling method was used to carry out the dynamic numerical simulation study of NPR（negative Poisson’s ratio） bolt/cable for the first time. Numerical models of two support schemes of PR and NPR bolt/cable were established, and the stress and displacement of the surrounding rock of the chamber and the bolt/cable under dynamic loads were compared and analyzed. The results show that under the impact load of 25 MPa, 21 of the 25 PR support bolts/cables failed, the surrounding rock was damaged in a large area, the coupling wall was severely deformed, and the chamber presented inner convex arc-shaped deformation and failure. Under the same conditions, none of the NPR bolts/cables failed, and the stability of the surrounding rock of the chamber remained good. [ABSTRACT FROM AUTHOR]

Since the left ventricle pressure waveform（LVPW）estimation is based on the model with numerous patient specific parameters, there is a great need to reduce the computation cost. A parameter subset selection strategy based on sensitivity analysis is proposed to solve these problems. LVPW features are chosen as outputs of a systemic circulation model. The meta model is created by adaptive sparse polynomial chaos expansion algorithm, and then Sobol sensitivity index is computed. Finally, the parameters which have large impact on LVPW features are selected as parameter subset. The parameter subset selection proposed in this paper can provide help for applying model to patient specific situations in clinical applications. Meantime, the results indicate that the reducing size of parameter subset can decrease the complex computation of parameter optimization significantly. Furthermore, LVPW estimation based on the proposed method has high correlation with that based on full model parameters. [ABSTRACT FROM AUTHOR]

Focusing on foggy images with low contrast and blurry detail, this paper decomposes the images into texture layer and structural layer firstly. Then the structural layer containing most of the fog is dehazed, and the texture layer is enhanced. To avoid the effect of white objects in the scene on atmospheric light estimation, this paper proposes a kind of stereo decision map in RGB space, and designs an atmospheric light estimation method which can adaptively distinguish between sky and non-sky area based on a threshold constraining scheme. Due to the inefficiency of dark channel prior when dealing with large areas of sky and dense fog, a transmission estimation approach based on middle channel compensation is put forward, which can avoid color distortion of dehazed images. Furthermore, the transmission is refined by the guided filtering with side window, which can preserve image details. Extensive experimental results show that the proposed approach can realize haze removal thoroughly, and the dehazed image has natural colors and vivid details. [ABSTRACT FROM AUTHOR]

Collecting wearable motion sensor signals and using transfer learning to overcome the inconsistency of data distribution to identify the daily behavior of the human body are very popular technologies. Using wearable sensors to collect signals will result in generating noise samples that affect the transfer effect. Traditional algorithms lack the processing of these samples. To solve this problem， the traditional algorithm was improved by introducing a sample screening algorithm based on Mahalanobis distance， and a transfer learning algorithm T-WMD was proposed that can be used for human activity recognition. And compared with other five algorithms on two public human activity recognition data sets， the results show that the algorithm proposed in this paper can effectively improve the effect of transfer learning. [ABSTRACT FROM AUTHOR]

Taking the medium deep hole mining in steeply narrow vein of a gold mine in Inner Mongolia as the engineering background, through empirical analogies, numerical simulation and field tests methods, the evolution law of cracks in narrow veins of deep hole blasting under different blasting parameters was analyzed, and the relationship between the blasting parameters and the over-under-excavation percentage of blasting, the density of blasting cracks and the vibration velocity of the surrounding rock particles is obtained. The results show that: when the hole spacing is 1. 2 - 1. 4 m, the over-under-excavation blasting area tends to be zero. When the burdern is 0. 8 - 1. 0 m, the blasting fragmentation is more uniform. A burden of 1. 0 m and a hole spacing of 1. 2 m can be taken as optimal parameters during deep hole blasting. The field blasting test also verifies the research results of this paper. [ABSTRACT FROM AUTHOR]

Aiming at the problem of inaccurate locating of traditional iris locating algorithms, an improved YOLOV3 iris locating model is proposed to improve the accuracy of iris locating and make it better applied to production practice. Using the Densenet-121 model as the feature extraction module, and on the basis of it, the auxiliary network is obtained by copying the backbone network to make it more conducive to the detection of small targets, and the non-local attention mechanism is used to enhance the semantic information of the features obtained by the image. The YOLOV3 model, Daugman model and Wilde model based on DarkNet-53 are used for comparative experiments. The experimental results show that the accuracy of the experimental model in this paper is as high as 97. 1 % in iris locating, which has obvious advantages compared with other iris locating models. [ABSTRACT FROM AUTHOR]

Although deep learning-based methods have made great progresses in the field of single image deraining, existing methods still have some problems such as loss of detail and residue of rain streaks. To overcome these short-comings, this paper proposed an adaptive perceptual pyramid network to remove dense rain streaks while revising image details at the same time and thus significantly improve the visual quality. Firstly, a multi-scale pyramid network with progressive connected sub-networks is constructed based on wavelet transform to extract and remove rain streaks iteratively. Each sub-network with the adaptive rain streak perceptual block as its core module is constructed through symmetric skip-connection to extract the shallow layer features to deeper layers to be reused. The adaptive rain streak perceptual block uses non-local operation and shared dilated convolution to expand the receptive fields, which can effectively perceive and remove rain streak adaptively. In order to remove rain streaks with different scales and impose some constrains of the network training, a multi-scale loss function is designed so as to gradually remove rain streaks from coarse to fine, which can effectively prevent artifacts. Extensive experimental results on synthetic and real datasets demonstrate the superiority of the proposed method over the state-of-the-art methods, which can remove rain streaks effectively with preserving vivid image details. [ABSTRACT FROM AUTHOR]

The ECGP wave contains abundant physiological and pathological information of the human body, but the P wave amplitude is small and the shape is changeable, which is very difficult to detect. This paper proposes a bilateral long-short-window energy difference method to detect multi-modal P wave boundaries, and uses the particle swarm algorithm to optimize its parameters. 4363 and 1936 ECG beats are selected from the LUE database and QT database respectively, with 70% and 30% of them used as the training set and the test set, respectively. Compared with the parameter-mixed Gaussian fitting method based on dynamic programming and the phase-free stationary wavelet transform method, the error of the results of positive and negative P waves is significantly smaller than the above two methods, and the algorithm can detect bidirectional P waves, and it also has anti-noise ability. [ABSTRACT FROM AUTHOR]

In response to the urgent need for large-scale open collaboration and resource sharing between distributed enterprises under the cloud manufacturing mode, this paper combines evolutionary game theory to establish an incentive mechanism for resource sharing in a distributed environment, and analyzes the evolutionary game trend of resource sharing in different situations. It can be known through theoretical analysis and simulation experiment that total shareable resources, resource sharing level, resource utilization capacity, synergy benefit coefficient, evaluation benefit coefficient, sharing incentive coefficient and speculative penalty coefficient play positive roles in promoting the resource sharing, while the shared cost coefficient plays a negative role and direct benefit level has no effect. There is an inverted U-shaped relationship between the allocation coefficient of synergy benefit and the stable state of resource sharing evolution. This study provides references for promoting distributed resource sharing and accelerating industrial innovation in the future cloud manufacturing mode. [ABSTRACT FROM AUTHOR]

CAN( controller area network) bus is the most widely used field bus. Due to the lack of authentication and message checking mechanism, CAN bus has great security risks, so it is necessary to design a defense mechanism for CAN bus. In this paper, a priority hopping mechanism is designed, which introduces the dynamic hopping of identifiers by Hash function into a real-time scheduling algorithm. The fixed priority is calculated by a genetic algorithm, and the compromise range of priority is found out. Each frame is grouped, and the ID segment of data frame is segmented and reconstructed. The former part of the ID segment determines the priority and performs priority hopping, while the latter part of the ID segment hops dynamically at one time. Experimental results show that using dynamic priority and one-time ID Hopping to hop has a greater security improvement than the existing ID Hopping mechanism. [ABSTRACT FROM AUTHOR]

In general adversarial attacks oriented to sample sets, the general perturbation design that causes most sample to output errors is the key to the research. This paper takes the typical convolutional neural networks as the research object, summarizes the existing general perturbation generation algorithms, and proposes a general perturbation generation algorithm that combines batch random gradient ascent and spherical projection search. In each iteration of the algorithm, a small batch of samples are extracted from the sample set, and the general perturbation is calculated by using the random gradient rising strategy which reduces the value of the loss function. The general perturbation is then projected to the high-dimensional spherical surface with a radius of ε, so as to reduce the search space of general disturbances. The algorithm also introduces a regularization technique to improve the generation quality of general disturbances. Experimental results show that compared with the baseline algorithm, the attack success rate is significantly increased, and the solution efficiency of general perturbation is improved by about 30 times. [ABSTRACT FROM AUTHOR]

The multi-scale quantum harmonic oscillator optimization algorithm(MQHOA)is a natural calculation algorithm based on quantum physics proposed in recent years. Aiming at the problem that the algorithm fails to make full use of the historical information in the iteration, this paper proposes a historical information-driven multi-scale quantum harmonic oscillator optimization algorithm(HI-MQHOA). In the two-step iterative process, HI-MQHOA introduces historical data as a driver to form the parameters of the next generation individual distribution and dynamically adjust the scale of the algorithm. The next generation individual distribution parameters can effectively guide the development and exploration of the algorithm, and dynamic scaling can avoid premature stagnation. Verified by several classical test functions, the algorithm is superior to MQHOA, improved MQHOA and other natural computing algorithms in solution quality, accuracy and scalability. [ABSTRACT FROM AUTHOR]

With the maturation of 3D technology and the popularization of smart mobile phones and other mobile devices， augmented reality (AR) technology has been rapidly developed. Aiming at English learning of young children， this paper discussed the functions and the methods of mobile AR applications. Though the experimental comparisons of different degrees of memorization on the teaching contents among preschool students， with one group using AR teaching while the other learning from paper books， then explore the advantages of the AR teaching methods. The results show that using AR teaching has more advantages for all ages of young children on the average number of remembering English words than with traditional teaching methods. What is more， this conclusion among the younger is more obvious; the forgetting rate in English words is smaller after the same time; with the increase of children's ages， the forgetting rate of English words reduces. [ABSTRACT FROM AUTHOR]

Based on the equivalent circuit model, the estimation method of the remaining state of charge (SOC) of a type of vehicle power battery shows that the estimation accuracy is highly dependent on the model accuracy and the model accuracy is directly proportional to the model complexity, so that it is difficult to be better applied to the embedded control unit problem. A new equivalent circuit model with relatively low complexity and capable of adaptively determining the optimal model order, i. e., a gray box model of the equivalent circuit of the vehicle power battery based on the order adaptive AR model is proposed. Based on this gray box model, the design derivation of the sliding mode observer for the state of lithium-ion battery SOC and the proof of observability and convergence are given. The results show that the sliding mode observer SOC estimation method (adaptive autoregressive-sliding mode observer, AAR-SMO) based on the order-adaptive equivalent circuit gray box model proposed in this paper has low model complexity, high accuracy, strong robustness and fast convergence performance. [ABSTRACT FROM AUTHOR]

To improve the comfort of the cabin space in aircraft， focusing on the difficulty to directly collect anthropometric data of head/neck posture angle， a method is proposed in this paper to obtain the head/neck posture angle indirectly by 3D scanning. A 3D scanning and a perceived level of discomfort(PLD)test are combined with a questionnaire， the results of which show that most passengers think that the current tray table is too low and uncomfortable. When tested with original height(68cm)tray table， the subjects’ head/neck posture angles are all outside the neutral region， indicating that the head/neck posture is excessive flexion. After tray table is raised gradually(73-78-83cm)and the same tests are repeated， the subjects’ HFA and NFA decreased significantly. The HFA and NFA are closer to or reach the neutral range. In PLD tests， with the rise of the tray table， the data first decreases and then rises. It shows that adjusting the tray table in 73~83cm can significantly improve the passengers’ head/neck posture and reduce the discomfort of passengers’ neck. [ABSTRACT FROM AUTHOR]

The filtration performance of bag filter for fly ash from power plants can be improved by unipolar charger. In this paper， hybrid electrostatic filter comprised of pre-charger and fibrous filter were designed and manufactured. Under different charge types， applied voltages and flow velocities， collection efficiency and pressure drop of PPS fibrous filter for unipolarly charged fly ash particles were investigated. The results indicated that with the increase of the applied voltage and the decrease of filtration velocity， the collection efficiency of bag filter is improved， and the growth rate of pressure increment is significantly reduced. The smaller the particle size， the more obvious the increase in the filtration effect， and the improvement effect of negatively charged particles is better than that of positively charged particles. [ABSTRACT FROM AUTHOR]

The information of step line is of great importance to open-pit mining. The existing method of obtaining step line has large workload， low efficiency and poor accuracy， which reduces the production efficiency and acceptance accuracy of the mine.Thus， a method of automatically extracting open-pit mine step lines from the dense point cloud data of open-pit mines generated by sequence UAV images is proposed in this paper. This method uses progressive morphological filtering algorithm to preprocess the point cloud， and a three-dimensional edge detection and curvature index weighting method that takes into account the geometric properties of the neighborhood is proposed to extract the feature points of the step line， then， it uses the moving least squares method to accurately fit the step line. The experimental results show that the algorithm can automatically， efficiently and accurately extract the step line of the open-pit mine， and generate open-pit mining status map. It has important application value for open-pit mine production and safety. [ABSTRACT FROM AUTHOR]

There are some limitations of key technologies in small object detection， multi-category object detection， and especially lightweight models. To solve these problems， this paper proposes a lightweight adaptive feature selection network for object detection. The network is constructed to extract multi-scale features based on the feature pyramid. To alleviate the noise interference and preserve the detail information， a feature selection module composed of spatial adaptation and channel adaptation is designed. Specifically， the feature maps are filtered from spatial dimension， encoded and decoded in channel dimension for selecting the meaningful features adaptively. Besides， the classification network is constructed through depth-wise separable convolution to reduce the computational cost， improve detection efficiency and realize the lightweight version of the network. The detection accuracy on the PASCAL VOC 2007 dataset is 77.7% in mean average precision(mAP)， and the detection speed is 14.3 in frames per second(FPS). The results on the MS COCO dataset show that the proposed network outperforms FPN and Mask R-CNN at the cost of 5% accuracy loss and achieves a better balance between accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Since it is difficult to online measure the underflow concentration of the thickener in the thickening-dehydration process, a broad learning system(BLS) based soft sensor modeling method is proposed in this paper. The method has high precision and strong generalization capability. First, several pressure sensors are installed inside the thickener, and the historical dataset under normal operating conditions is established. Then, the soft sensor model is trained by employing the BLS method to online predict the underflow concentration of the thickener. Finally, the efficiency of the proposed method is verified by simulation experiments. Compared with other traditional machine learning methods, the BLS method has higher prediction accuracy. [ABSTRACT FROM AUTHOR]

In order to study the pressure distribution and evolution of the wall and the corridor in the squat silo with ground conveying corridor, a full-scale silo loading and unloading test and simulation were carried out. It was found that the pressure distribution at the bottom of the wall is affected by the existence of the corridors. The pressure of the corridor is related directly to the actual height of the stored material above it. Rankine' s coefficient of active earth pressure is more suitable to predict the lateral pressure on the wall and the corridor. The basis for distinguishing the deep and shallow buried tunnels is not applicable to the conveying corridor in the squat silo where the arch effect of the stored material is not obvious. The predicted value of the top wall pressure on the corridor according to highway tunnel code and Terzaghi' s theory is far from the actual test value. It is more reasonable and safer to use the corridor pressure calculation formula proposed in this paper based on the shallow buried theory. There are different degrees of overpressure on the top wall and the side wall of the main and secondary corridors during eccentric discharge. It is recommended that the overpressure coefficient of the corridors should be properly considered when calculating the discharge load in squat silos. [ABSTRACT FROM AUTHOR]