Application of artificial intelligent systems for real power transfer allocation

The application of various artificial intelligent（AI） techniques,namely artificial neural network（ANN）,adaptive neuro fuzzy interface system（ANFIS）,genetic algorithm optimized least square support vector machine（GA-LSSVM） and multivariable regression（MVR） models was presented to identify the real power transfer between generators and loads.These AI techniques adopt supervised learning,which first uses modified nodal equation（MNE） method to determine real power contribution from each generator to loads.Then the results of MNE method and load flow information are utilized to estimate the power transfer using AI techniques.The 25-bus equivalent system of south Malaysia is utilized as a test system to illustrate the effectiveness of various AI methods compared to that of the MNE method.     

Predicting configuration performance of modular product family using principal component analysis and support vector machine

A novel configuration performance prediction approach with combination of principal component analysis（PCA） and support vector machine（SVM） was proposed.This method can estimate the performance parameter values of a newly configured product through soft computing technique instead of practical test experiments,which helps to evaluate whether or not the product variant can satisfy the customers＇ individual requirements.The PCA technique was used to reduce and orthogonalize the module parameters that affect the product performance.Then,these extracted features were used as new input variables in SVM model to mine knowledge from the limited existing product data.The performance values of a newly configured product can be predicted by means of the trained SVM models.This PCA-SVM method can ensure that the performance prediction is executed rapidly and accurately,even under the small sample conditions.The applicability of the proposed method was verified on a family of plate electrostatic precipitators.     

Fuzzy least squares support vector machine soft measurement model based on adaptive mutative scale chaosimmune algorithm简

In order to enhance measuring precision of the real complex electromechanical system,complex industrial system and complex ecological management system with characteristics of multi-variable,non-liner,strong coupling and large time-delay,in terms of the fuzzy character of this real complex system,a fuzzy least squares support vector machine（FLS-SVM） soft measurement model was established and its parameters were optimized by using adaptive mutative scale chaos immune algorithm.The simulation results reveal that fuzzy least squares support vector machines soft measurement model is of better approximation accuracy and robustness.And application results show that the relative errors of the soft measurement model are less than 3.34%.     

Shadow detection combining characters of human vision简

A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network（PCNN） by both subjective and objective assessments.     

Preparation and characterization of Andalusite ceramic used for solar thermal power generation

High-temperature thermal storage material is one of the critical materials of solar thermal power generation system. Andalusite, kaolin, talc, γ-Al 2 O 3 and partially stabilized zirconia were used as the raw materials, and in-situ synthesis of cordierite was adopted to fabricate thermal storage material for solar thermal power generation via pressureless sintering. The phase compositions, microstructures and thermal shock resistances of the sintered samples were analyzed by XRD, SEM and EDS, and the corresponding mechanical properties were measured. The results show that the major phases of the samples are mullite and zirconium silicate, and the pores distribute uniformly. After being sintered at 1 460 ℃, A4 sample exhibits a better mechanical performance and thermal shock resistance, its loss rate of bending strength after 30 cycles thermal shock is 3.04%, the bulk density and bending strength are 2.86 g·cm-3 and 139.66 MPa, respectively. The better thermal shock resistance of the sample is closely related to the effect of zirconium silicate, such as its uniform distribution, nested growth with mullite, low thermal expansion coeffi cient, high thermal conductivity, etc. This ceramic can be widely used as one of potential thermal storage materials of solar thermal power generation system.     

Fracture toughness and fracture behavior of SA508-Ⅲ steel at different temperatures

The fracture toughness of SA508-Ⅲ steel was studied in the temperature range from room temperature to 320℃ using the J-integral method. The fracture behavior of the steel was also investigated. It was found that the conditional fracture toughness （JQ） of the steel first decreased and then increased with increasing test temperature. The maximum and minimum values of do were 517.4 kJ/m^2 at 25℃ and 304.5 kJ/m^2 at 180℃, respectively. Dynamic strain aging （DSA） was also observed to occur when the temperature exceeded 260℃ with a certain strain rate. Both the dislocation density and the number of small dislocation cells effectively increased because of the occurrence of DSA; as a consequence, crack propagation was more strongly inhibited in the steel. Simultaneously, an increasing number of fine carbides precipitated under high stress at temperatures greater than 260℃. Thus, the deformation resistance of the steel was improved and the Jo was enhanced.     

Mapping methods for output-based objective speech quality assessment using data mining

Objective speech quality is difficult to be measured without the input reference speech. Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm. The degraded speech is firstly separated into three classes （unvoiced, voiced and silence）, and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining. Fuzzy Gaussian mixture model （GMM） is used to generate the artificial reference model trained on perceptual linear predictive （PLP） features. The mean opinion score （MOS） mapping methods including multivariate non-linear regression （MNLR）, fuzzy neural network （FNN） and support vector regression （SVR） are designed and compared with the standard ITU-T P.563 method. Experimental results show that the assessment methods with data mining perform better than ITU-T P.563. Moreover, FNN and SVR are more efficient than MNLR, and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.     

An analysis method for correlation between catenary irregularities and pantograph-catenary contact force

Pantograph-catenary contact force provides the main basis for evaluation of current quality collection; however, the pantograph-catenary contact force is largely affected by the catenary irregularities. To analyze the correlated relationship between catenary irregularities and pantograph-catenary contact force, a method based on nonlinear auto-regressive with exogenous input （NARX） neural networks was developed. First, to collect the test data of catenary irregularities and contact force, the pantograph/catenary dynamics model was established and dynamic simulation was conducted using MATLAB/Simulink. Second, catenary irregularities were used as the input to NARX neural network and the contact force was determined as output of the NARX neural network, in which the neural network was trained by an improved training mechanism based on the regularization algorithm. The simulation results show that the testing error and correlation coefficient are 0.1100 and 0.8029, respectively, and the prediction accuracy is satisfactory. And the comparisons with other algorithms indicate the validity and superiority of the proposed approach.     

Two-stage stochastic approach for spinning reserve allocation in dynamic economic dispatch简

A novel approach was proposed to allocate spinning reserve for dynamic economic dispatch.The proposed approach set up a two-stage stochastic programming model to allocate reserve.The model was solved using a decomposed algorithm based on Benders＇ decomposition.The model and the algorithm were applied to a simple 3-node system and an actual 445-node system for verification,respectively.Test results show that the model can save 84.5 US $ cost for the testing three-node system,and the algorithm can solve the model for 445-node system within 5 min.The test results also illustrate that the proposed approach is efficient and suitable for large system calculation.     

Reconstruction based approach to sensor fault diagnosis using auto-associative neural networks

Fault diagnostics is an important research area including different techniques. Principal component analysis （PCA） is a linear technique which has been widely used. For nonlinear processes, however, the nonlinear principal component analysis （NLPCA） should be applied. In this work, NLPCA based on auto-associative neural network （AANN） was applied to model a chemical process using historical data. First, the residuals generated by the AANN were used for fault detection and then a reconstruction based approach called enhanced AANN （E-AANN） was presented to isolate and reconstruct the faulty sensor simultaneously. The proposed method was implemented on a continuous stirred tank heater （CSTH） and used to detect and isolate two types of faults （drift and offset） for a sensor. The results show that the proposed method can detect, isolate and reconstruct the occurred fault properly.     

Interference management via access control and mobility prediction in two-tier heterogeneous networks

Abstract： Two-tier heterogeneous networks （HetNets）, where the current cellular networks, i.e., macrocells, are overlapped with a large number of randomly distributed femtocells, can potentially bring significant benefits to spectral utilization and system capacity. The interference management and access control for open and closed femtocells in two-tier HetNets were focused. The contributions consist of two parts. Firstly, in order to reduce the uplink interference caused by MUEs （macrocell user equipments） at closed femtocells, an incentive mechanism to implement interference mitigation was proposed. It encourages femtoeells that work with closed-subscriber-group （CSG） to allow the interfering MUEs access in but only via uplink, which can reduce the interference significantly and also benefit the marco-tier. The interference issue was then studied in open-subscriber-group （OSG） femtocells from the perspective of handover and mobility prediction. Inbound handover provides an alternative solution for open femtocells when interference turns up, while this accompanies with PCI （physical cell identity） confusion during inbound handover. To reduce the PCI confusion, a dynamic PCI allocation scheme was proposed, by which the high handin femtocells have the dedicated PCI while the others share the reuse PCIs. A Markov chain based mobility prediction algorithm was designed to decide whether the femtoeell status is with high handover requests. Numerical analysis reveals that the UL interference is managed well for the CSG femtocell and the PCI confusion issue is mitigated greatly in OSG femtocell compared to the conventional approaches.     

Two new methods for power flow tracing using bus power balance equations

Two new methods were presented for power flow tracing（PFT）.These two methods were compared and the results were discussed in detail.Both methods use the active and reactive power balance equations at each bus in order to solve the tracing problem.The first method considers the proportional sharing assumption while the second one uses the circuit laws to find the relationship between power inflows and outflows through each line,generator and load connected to each bus of the network.Both methods are able to handle loop flow and loss issues in tracing problem.A formulation is also proposed to find the share of each unit in provision of each load.These methods are applied to find the producer and consumer＇s shares on the cost of transmission for each line in different case studies.As the results of these studies show,both methods can effectively solve the PFT problem.     

Experimental investigation of power micro-emulsification diesel output and soot emission for oil using for vehicle

The micro-emulsification diesel oil with water dopant of 5%, 10% and 15% was prepared using the NAA micro-emulsification compound developed by the authors. The engine bench testing was carried out on the 485QB diesel engine. From the testing results of velocity, loading and exhaust gas, it can be seen that the power decreases and the fuel consumption increases using the micro-emulsification diesel oil. But based on the actual fuel consumption, the use of emulsification diesel with water dopant of 10% can get the effect of oil saving; while with water donant of more than 15% , it doesnt work evidently. The investigation shows that using the micro - emulsification diesel oil, we can reduce the exhaust gas pollution and receive better environment benefit.     

Influence of lateral initial pressure on axisymmetric wave propagation in hollow cylinder based on first powerhypo-elastic model简

Influence of identical applied initial pressures on the radial surfaces of a hollow cylinder which is compose of materials with first power hypo-elastic constitutive model was investigated.The basic equations of the problem were built up based on the framework of piecewise homogeneous body model with the use of three-dimensional linearized theory of elastic waves in initially stressed bodies（TLTEWISB）.With the method proposed previously,this problem was then solved numerically.Moreover,the dispersion group velocity of the lowest order mode with different initial pressures was also studied.It can be concluded that the initial pressure and the geometry parameters will induce considerable changes of different degrees in dispersive relation between phase velocity and wave number in opposite trend（positive in initial pressure and negative in thickness）.     

Fabrication and densification enhancement of SiC-particulate-reinforced copper matrix composites prepared via the sinter-forging process

The fabrication of copper （Cu） and copper matrix silicon carbide （Cu/SiCp） particulate composites via the sinter-forging process was investigated. Sintering and sinter-forging processes were performed under an inert Ar atmosphere. The influence of sinter-forging time, temperature, and compressive stress on the relative density and hardness of the prepared samples was systematically investigated and subsequently compared with that of the samples prepared by the conventional sintering process. The relative density and hardness of the composites were enhanced when they were prepared by the sinter-forging process. The relative density values of all Cu/SiCp composite samples were observed to decrease with the increase in SiC content.     

Effects of magnetic fields on Fe-Si composite electrodeposition

Coatings containing Fe-Si particles were electrodeposited on 3.0wt% Si steel sheets under magnetic fields. The effects of magnetic flux density （MFD）, electrode arrangement and current density on the surface morphology, the silicon content in the coatings and the cathode current efficiency were investigated. When a magnetic field was applied parallel to the current and when the MFD was less than 0.5 T, numerous needle-like structures appeared on the coating surface. With increasing MFD, the needle-like structures weakened and were transformed into dome-shaped structures. Meanwhile, compared to results obtained in the absence of a magnetic field, the silicon content in the coatings significantly increased as the MFD was increased for all of the samples obtained using a vertical electrode system. However, in the case of an aclinic electrode system, the silicon content decreased. Furthermore, the cathode current efficiency was considerably diminished when a magnetic field was applied. A possible mechanism for these phenomena was discussed.     

Dielectric,piezoelectric, and ferroelectric properties of lanthanum-modified PZTFN ceramics

Specimens of Pb1-1.5xLax（Zr0.53 Ti0.47）1-y-zFeyNb2O3 （x = 0, 0.004, 0.008, 0.012, and 0.016, y = z = 0.01） （PZTFN） ceramics were synthesized by a semi-wet route. In the present study, the effect of La doping was investigated on the structural, microstructural, dielectric, piezoelectric, and ferroelectric properties of the ceramics. The results show that, the tetragonal （space group P4mm） and rhombohedral （space group R3c） phases are observed to coexist in the sample at x = 0.012. Microstructural investigations of all the samples reveal that La doping inhibits grain growth. Doping of La into PZTFN improves the dielectric, ferroelectric, and piezoelectric properties of the ceramics. The hys- teresis loops of all specimens exhibit nonlinear behavior. The dielectric, piezoelectric and ferroelectric properties show a maximum response atx 〉 0.012, which corresponds to the morphotropic phase boundary （MPB）.     

Effects of sintering temperature on the microstructural evolution and wear behavior of WCp reinforced Ni-based coatings

This article focuses on the microstructural evolution and wear behavior of 50wt%WC reinforced Ni-based composites prepared onto 304 stainless steel substrates by vacuum sintering at different sintering temperatures. The microstructure and chemical composition of the coatings were investigated by X-ray diffraction （XRD）, differential thermal analysis （DTA）, scanning and transmission electron microscopy （SEM and TEM） equipped with energy-dispersive X-ray spectroscopy （EDS）. The wear resistance of the coatings was tested by thrust washer testing. The mechanisms of the decomposition, dissolution, and precipitation of primary carbides, and their influences on the wear resistance have been discussed. The results indicate that the coating sintered at 1175℃ is composed of fine WC particles, coarse M6C （M=Ni, Fe, Co, etc.） carbides, and discrete borides dispersed in solid solution. Upon increasing the sintering temperature to 1225℃, the microstructure reveals few incompletely dissolved WC particles trapped in larger M6C, Cr-rich lamellar M23C6, and M3C2 in the austenite matrix. M23C6 and M3C2 precipitates are formed in both the γ/M6C grain boundary and the matrix. These large-sized and lamellar brittle phases tend to weaken the wear resistance of the composite coatings. The wear behavior is controlled simultaneously by both abrasive wear and adhesive wear. Among them, abrasive wear plays a major role in the wear process of the coating sintered at 1175℃, while the effect of adhesive wear is predominant in the coating sintered at 1225℃.     

Fluidized bed coating efficiency and morphology of coatings for producing Al-based nanocomposite hollow spheres

Abstract： We performed fluidized bed coating ofAl-based nanoeomposite powder-binder suspensions onto polymer substrates. The effects of the type and amount of the binder and nanoparticle additive on the coating process efficiency and coating characteristics were investigated. The efficiency decreased from 52% to 49% as the processing time increased from 15 to 20 min. However, the amount and thickness of the coating also increased as the processing time and amount of the binder were increased. The addition of nanoparticles to the system decreased the thickness of the coating from 222 to 207 μm when polyvinyl alcohol （PVA） was used as a binder. The suspension containing 3wt% R-4410 binder exhibited the greatest efficiency of 60%.     

High-temperature performance prediction of iron ore fines and the ore-blending programming problem in sintering

The high-temperature performance of iron ore fmes is an important factor in optimizing ore blending in sintering. However, the application of linear regression analysis and the linear combination method in most other studies always leads to a large deviation from the desired results. In this study, the fuzzy membership functions of the assimilation ability temperature and the liquid fluidity were proposed based on the fuzzy mathematics theory to construct a model for predicting the high-temperature performance of mixed iron ore. Comparisons of the prediction model and experimental results were presented. The results illustrate that the prediction model is more accurate and effective than previously developed models. In addition, fuzzy constraints for the high-temperature performance of iron ore in this research make the results of ore blending more comparable. A solution for the quantitative calculation as well as the programming of fuzzy constraints is also introduced.